修改了一些bug

This commit is contained in:
Jackson.Bruce
2020-03-17 19:25:37 +08:00
parent 3261aa0c71
commit 42f0013608
32 changed files with 34494 additions and 10 deletions

View File

@@ -3,12 +3,35 @@
<PropertyGroup>
<TargetFramework>netcoreapp3.1</TargetFramework>
<RootNamespace>Ufangx.Xss</RootNamespace>
<Authors>Jackson.bruce</Authors>
<PackageProjectUrl>https://github.com/JacksonBruce/AntiXssUF</PackageProjectUrl>
<RepositoryUrl>https://github.com/JacksonBruce/AntiXssUF.git</RepositoryUrl>
<RepositoryType>git</RepositoryType>
<Description>anti xss mvc model binder policy</Description>
<PackageTags>anti xss mvc model binder policy</PackageTags>
<Company>ufangx</Company>
<Copyright>Copyright (c) 2020 Jackson.Bruce</Copyright>
<PackageReleaseNotes>https://github.com/JacksonBruce/AntiXssUF/blob/master/README.md</PackageReleaseNotes>
<Version>1.0.0-beta.0</Version>
<GeneratePackageOnBuild>true</GeneratePackageOnBuild>
</PropertyGroup>
<ItemGroup>
<Compile Remove="AntiXssUFMvcServiceCollectionExtensions.cs" />
</ItemGroup>
<ItemGroup>
<None Remove="resources\antixss-policy-Default.json" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="resources\antixss-policy-Default.json">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
<ExcludeFromSingleFile>true</ExcludeFromSingleFile>
<CopyToPublishDirectory>PreserveNewest</CopyToPublishDirectory>
</EmbeddedResource>
</ItemGroup>
<ItemGroup>
<PackageReference Include="Microsoft.AspNetCore.Mvc.Abstractions" Version="2.2.0" />
<PackageReference Include="Microsoft.AspNetCore.Mvc.Core" Version="2.2.5" />
@@ -18,4 +41,34 @@
<ProjectReference Include="..\AntiXssUF\AntiXssUF.csproj" />
</ItemGroup>
<ItemGroup>
<None Update="resources\antixss-policy-antisamy-anythinggoes.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-antisamy-ebay.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-antisamy-myspace.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-antisamy-slashdot.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-antisamy-test.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-antisamy.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-Default.config">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy-Default.xml">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="resources\antixss-policy.xsd">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
</ItemGroup>
</Project>

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,176 @@
<?xml version="1.0" encoding="ISO-8859-1"?>
<!--
W3C rules retrieved from:
http://www.w3.org/TR/html401/struct/global.html
-->
<!--
Slashdot allowed tags taken from "Reply" page:
<b> <i> <p> <br> <a> <ol> <ul> <li> <dl> <dt> <dd> <em> <strong> <tt> <blockquote> <div> <ecode> <quote>
-->
<anti-samy-rules xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="antixss-policy.xsd">
<directives>
<directive name="omitXmlDeclaration" value="true"/>
<directive name="omitDoctypeDeclaration" value="true"/>
<directive name="maxInputSize" value="5000"/>
<directive name="useXHTML" value="true"/>
<directive name="formatOutput" value="true"/>
<directive name="embedStyleSheets" value="false"/>
</directives>
<common-regexps>
<!--
From W3C:
This attribute assigns a class name or set of class names to an
element. Any number of elements may be assigned the same class
name or names. Multiple class names must be separated by white
space characters.
-->
<regexp name="htmlTitle" value="[\p{L}\p{N}\s-_',:\[\]!\./\\\(\)]*"/> <!-- force non-empty with a '+' at the end instead of '*' -->
<regexp name="onsiteURL" value="([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)"/>
<regexp name="offsiteURL" value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*"/>
</common-regexps>
<!--
Tag.name = a, b, div, body, etc.
Tag.action = filter: remove tags, but keep content, validate: keep content as long as it passes rules, remove: remove tag and contents
Attribute.name = id, class, href, align, width, etc.
Attribute.onInvalid = what to do when the attribute is invalid, e.g., remove the tag (removeTag), remove the attribute (removeAttribute), filter the tag (filterTag)
Attribute.description = What rules in English you want to tell the users they can have for this attribute. Include helpful things so they'll be able to tune their HTML
-->
<!--
Some attributes are common to all (or most) HTML tags. There aren't many that qualify for this. You have to make sure there's no
collisions between any of these attribute names with attribute names of other tags that are for different purposes.
-->
<common-attributes>
<attribute name="lang" description="The 'lang' attribute tells the browser what language the element's attribute values and content are written in">
<regexp-list>
<regexp value="[a-zA-Z]{2,20}"/>
</regexp-list>
</attribute>
<attribute name="title" description="The 'title' attribute provides text that shows up in a 'tooltip' when a user hovers their mouse over the element">
<regexp-list>
<regexp name="htmlTitle"/>
</regexp-list>
</attribute>
<attribute name="href" onInvalid="filterTag">
<regexp-list>
<regexp name="onsiteURL"/>
<regexp name="offsiteURL"/>
</regexp-list>
</attribute>
<attribute name="align" description="The 'align' attribute of an HTML element is a direction word, like 'left', 'right' or 'center'">
<literal-list>
<literal value="center"/>
<literal value="left"/>
<literal value="right"/>
<literal value="justify"/>
<literal value="char"/>
</literal-list>
</attribute>
</common-attributes>
<!--
This requires normal updates as browsers continue to diverge from the W3C and each other. As long as the browser wars continue
this is going to continue. I'm not sure war is the right word for what's going on. Doesn't somebody have to win a war after
a while?
-->
<global-tag-attributes>
<attribute name="title"/>
<attribute name="lang"/>
</global-tag-attributes>
<tag-rules>
<!-- Tags related to JavaScript -->
<tag name="script" action="remove"/>
<tag name="noscript" action="remove"/>
<!-- Frame & related tags -->
<tag name="iframe" action="remove"/>
<tag name="frameset" action="remove"/>
<tag name="frame" action="remove"/>
<tag name="noframes" action="remove"/>
<!-- CSS related tags -->
<tag name="style" action="remove"/>
<!-- All reasonable formatting tags -->
<tag name="p" action="validate">
<attribute name="align"/>
</tag>
<tag name="div" action="validate"/>
<tag name="i" action="validate"/>
<tag name="b" action="validate"/>
<tag name="em" action="validate"/>
<tag name="blockquote" action="validate"/>
<tag name="tt" action="validate"/>
<tag name="br" action="truncate"/>
<!-- Custom Slashdot tags, though we're trimming the idea of having a possible mismatching end tag with the endtag="" attribute -->
<tag name="quote" action="validate"/>
<tag name="ecode" action="validate"/>
<!-- Anchor and anchor related tags -->
<tag name="a" action="validate">
<attribute name="href" onInvalid="filterTag"/>
<attribute name="nohref">
<literal-list>
<literal value="nohref"/>
<literal value=""/>
</literal-list>
</attribute>
<attribute name="rel">
<literal-list>
<literal value="nofollow"/>
</literal-list>
</attribute>
</tag>
<!-- List tags -->
<tag name="ul" action="validate"/>
<tag name="ol" action="validate"/>
<tag name="li" action="validate"/>
</tag-rules>
<!-- No CSS on Slashdot posts -->
<css-rules>
</css-rules>
</anti-samy-rules>

View File

@@ -0,0 +1,862 @@
<?xml version="1.0" encoding="ISO-8859-1" ?>
<!--
W3C rules retrieved from:
http://www.w3.org/TR/html401/struct/global.html
-->
<anti-samy-rules xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="antixss-policy.xsd">
<directives>
<directive name="omitXmlDeclaration" value="true"/>
<directive name="omitDoctypeDeclaration" value="true"/>
<directive name="maxInputSize" value="20001"/>
<directive name="useXHTML" value="true"/>
<directive name="formatOutput" value="true"/>
<!--
remember, this won't work for relative URIs - AntiSamy doesn't
know anything about the URL or your web structure
-->
<directive name="embedStyleSheets" value="false"/>
</directives>
<common-regexps>
<!--
From W3C:
This attribute assigns a class name or set of class names to an
element. Any number of elements may be assigned the same class
name or names. Multiple class names must be separated by white
space characters.
-->
<regexp name="colorNameOrCode" value="(#[0-9a-fA-F]{6}|[a-zA-Z]{1,20})"/>
<regexp name="number" value="[0-9]+"/>
<regexp name="anything" value=".*"/>
<regexp name="numberOrPercent" value="(\d)+(%{0,1})"/>
<regexp name="paragraph" value="([\p{L}\p{N},'\.\s\-_\(\)]|&amp;[0-9]{2};)*"/>
<regexp name="htmlId" value="[a-zA-Z0-9-_]+"/>
<regexp name="htmlTitle" value="[\p{L}\p{N}\s-_',:\[\]!\./\\\(\)]*"/> <!-- force non-empty with a '+' at the end instead of '*' -->
<regexp name="htmlClass" value="[a-zA-Z0-9\s,-_]+"/>
<regexp name="onsiteURL" value="([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)"/>
<regexp name="offsiteURL" value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*"/>
<regexp name="boolean" value="(true|false)"/>
<regexp name="singlePrintable" value="[a-zA-Z0-9]{1}"/> <!-- \w allows the '_' character -->
<!-- This is for elements (ex: elemName { ... }) -->
<regexp name="cssElementSelector" value="[a-zA-Z0-9\-_]+|\*"/>
<!-- This is to list out any element names that are *not* valid -->
<regexp name="cssElementExclusion" value=""/>
<!-- This if for classes (ex: .className { ... }) -->
<regexp name="cssClassSelector" value="\.[a-zA-Z0-9\-_]+"/>
<!-- This is to list out any class names that are *not* valid -->
<regexp name="cssClassExclusion" value=""/>
<!-- This is for ID selectors (ex: #myId { ... } -->
<regexp name="cssIDSelector" value="#[a-zA-Z0-9\-_]+"/>
<!-- This is for ID selectors (ex: #myId { ... } -->
<regexp name="cssId" value="#[a-zA-Z0-9\-_]+"/>
<!-- This is to list out any IDs that are *not* valid - FIXME: What should the default be to avoid div hijacking? *? -->
<regexp name="cssIDExclusion" value=""/>
<!-- This is for pseudo-element selector (ex. foo:pseudo-element { ... } -->
<regexp name="cssPseudoElementSelector" value=":[a-zA-Z0-9\-_]+"/>
<!-- This is to list out any psuedo-element names that are *not* valid -->
<regexp name="cssPsuedoElementExclusion" value=""/>
<!-- This is for attribute selectors (ex. foo[attr=value] { ... } -->
<regexp name="cssAttributeSelector" value="\[[a-zA-Z0-9-_]+((=|~=|\|=){1}[a-zA-Z0-9\-_]+){1}\]"/>
<!-- This is to list out any attribute names that are *not* valid -->
<regexp name="cssAttributeExclusion" value=""/>
<!-- This is for resources referenced from CSS (such as background images and other imported stylesheets) -->
<regexp name="cssOnsiteUri" value="url\(([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)\)"/>
<regexp name="cssOffsiteUri" value="url\((\s)*((ht|f)tp(s?)://)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*\)"/>
<!-- This is for comments within CSS (ex. /* comment */) -->
<regexp name="cssCommentText" value="[\p{L}\p{N}-_,\/\\\.\s\(\)!\?\=\$#%\^&amp;:\[\]&quot;']+"/>
<regexp name="integer" value="(-|\+)?[0-9]+"/>
<regexp name="number" value="(-|\+)?([0-9]+(.[0-9]+)?)"/>
<regexp name="angle" value="(-|\+)?([0-9]+(.[0-9]+)?)(deg|grads|rad)"/>
<regexp name="time" value="([0-9]+(.[0-9]+)?)(ms|s)"/>
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>
<!--
Tag.name = a, b, div, body, etc.
Tag.action = filter: remove tags, but keep content, validate: keep content as long as it passes rules, remove: remove tag and contents
Attribute.name = id, class, href, align, width, etc.
Attribute.onInvalid = what to do when the attribute is invalid, e.g., remove the tag (removeTag), remove the attribute (removeAttribute), filter the tag (filterTag)
Attribute.description = What rules in English you want to tell the users they can have for this attribute. Include helpful things so they'll be able to tune their HTML
-->
<!--
Some attributes are common to all (or most) HTML tags. There aren't many that qualify for this. You have to make sure there's no
collisions between any of these attribute names with attribute names of other tags that are for different purposes.
-->
<common-attributes>
<!-- Common to all HTML tags -->
<attribute name="id" description="The 'id' of any HTML attribute should not contain anything besides letters and numbers">
<regexp-list>
<regexp value="[a-zA-Z0-9_\-\:]+"/>
</regexp-list>
</attribute>
<attribute name="class" description="The 'class' of any HTML attribute is usually a single word, but it can also be a list of class names separated by spaces">
<regexp-list>
<regexp name="htmlClass"/>
</regexp-list>
</attribute>
<attribute name="lang" description="The 'lang' attribute tells the browser what language the element's attribute values and content are written in">
<regexp-list>
<regexp value="[a-zA-Z]{2,20}"/>
</regexp-list>
</attribute>
<attribute name="title" description="The 'title' attribute provides text that shows up in a 'tooltip' when a user hovers their mouse over the element">
<regexp-list>
<regexp name="htmlTitle"/>
</regexp-list>
</attribute>
<attribute name="alt" description="The 'alt' attribute provides alternative text to users when its visual representation is not available">
<regexp-list>
<regexp name="paragraph"/>
</regexp-list>
</attribute>
<!-- the "style" attribute will be validated by an inline stylesheet scanner, so no need to define anything here - i hate having to special case this but no other choice -->
<attribute name="style" description="The 'style' attribute provides the ability for users to change many attributes of the tag's contents using a strict syntax"/>
<attribute name="media">
<literal-list>
<literal value="screen"/>
<literal value="tty"/>
<literal value="tv"/>
<literal value="projection"/>
<literal value="handheld"/>
<literal value="print"/>
<literal value="braille"/>
<literal value="aural"/>
<literal value="all"/>
</literal-list>
</attribute>
<!-- Anchor related -->
<!-- onInvalid="filterTag" has been removed as per suggestion at OWASP SJ 2007 - just "name" is valid -->
<attribute name="href">
<regexp-list>
<regexp name="onsiteURL"/>
<regexp name="offsiteURL"/>
</regexp-list>
</attribute>
<attribute name="name">
<regexp-list>
<regexp value="[a-zA-Z0-9-_\$]+"/>
<!--
have to allow the $ for .NET controls - although,
will users be supplying input that has server-generated
.NET control names? methinks not, but i want to pass my
test cases
-->
</regexp-list>
</attribute>
<attribute name="shape" description="The 'shape' attribute defines the shape of the selectable area">
<literal-list>
<literal value="default"/>
<literal value="rect"/>
<literal value="circle"/>
<literal value="poly"/>
</literal-list>
</attribute>
<!-- Table attributes -->
<attribute name="border">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="cellpadding">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="cellspacing">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="colspan">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="rowspan">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="background">
<regexp-list>
<regexp name="onsiteURL"/>
</regexp-list>
</attribute>
<attribute name="bgcolor">
<regexp-list>
<regexp name="colorNameOrCode"/>
</regexp-list>
</attribute>
<attribute name="abbrev">
<regexp-list>
<regexp name="paragraph"/>
</regexp-list>
</attribute>
<attribute name="headers" description="The 'headers' attribute is a space-separated list of cell IDs">
<regexp-list>
<regexp value="[a-zA-Z0-9\s*]*"/>
</regexp-list>
</attribute>
<attribute name="charoff">
<regexp-list>
<regexp value="numberOrPercent"/>
</regexp-list>
</attribute>
<attribute name="char">
<regexp-list>
<regexp value=".*{0,1}"/>
</regexp-list>
</attribute>
<attribute name="axis" description="The 'headers' attribute is a comma-separated list of related header cells">
<regexp-list>
<regexp value="[a-zA-Z0-9\s*,]*"/>
</regexp-list>
</attribute>
<attribute name="nowrap" description="The 'nowrap' attribute tells the browser not to wrap text that goes over one line">
<regexp-list>
<regexp name="anything"/>
<!-- <regexp value="(nowrap){0,1}"/> -->
</regexp-list>
</attribute>
<!-- Common positioning attributes -->
<attribute name="width">
<regexp-list>
<regexp name="numberOrPercent"/>
</regexp-list>
</attribute>
<attribute name="height">
<regexp-list>
<regexp name="numberOrPercent"/>
</regexp-list>
</attribute>
<attribute name="align" description="The 'align' attribute of an HTML element is a direction word, like 'left', 'right' or 'center'">
<literal-list>
<literal value="center"/>
<literal value="middle"/>
<literal value="left"/>
<literal value="right"/>
<literal value="justify"/>
<literal value="char"/>
</literal-list>
</attribute>
<attribute name="valign" description="The 'valign' attribute of an HTML attribute is a direction word, like 'baseline','bottom','middle' or 'top'">
<literal-list>
<literal value="baseline"/>
<literal value="bottom"/>
<literal value="middle"/>
<literal value="top"/>
</literal-list>
</attribute>
<!-- Intrinsic JavaScript Events -->
<attribute name="onFocus" description="The 'onFocus' event is executed when the control associated with the tag gains focus">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onBlur" description="The 'onBlur' event is executed when the control associated with the tag loses focus">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onClick" description="The 'onClick' event is executed when the control associated with the tag is clicked">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onDblClick" description="The 'onDblClick' event is executed when the control associated with the tag is clicked twice immediately">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onMouseDown" description="The 'onMouseDown' event is executed when the control associated with the tag is clicked but not yet released">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onMouseUp" description="The 'onMouseUp' event is executed when the control associated with the tag is clicked after the button is released">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onMouseOver" description="The 'onMouseOver' event is executed when the user's mouse hovers over the control associated with the tag">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="scope" description="The 'scope' attribute defines what's covered by the header cells">
<literal-list>
<literal value="row"/>
<literal value="col"/>
<literal value="rowgroup"/>
<literal value="colgroup"/>
</literal-list>
</attribute>
<!-- If you want users to be able to mess with tabindex, uncomment this -->
<!--
<attribute name="tabindex" description="...">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
-->
<!-- Input/form related common attributes -->
<attribute name="disabled">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="readonly">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="accesskey">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="size">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="autocomplete">
<literal-list>
<literal value="on"/>
<literal value="off"/>
</literal-list>
</attribute>
<attribute name="rows">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="cols">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
</common-attributes>
<!--
This requires normal updates as browsers continue to diverge from the W3C and each other. As long as the browser wars continue
this is going to continue. I'm not sure war is the right word for what's going on. Doesn't somebody have to win a war after
a while? Even wars of attrition, surely?
-->
<global-tag-attributes>
<!-- Not valid in base, head, html, meta, param, script, style, and title elements. -->
<attribute name="id"/>
<attribute name="style"/>
<attribute name="title"/>
<attribute name="class"/>
<!-- Not valid in base, br, frame, frameset, hr, iframe, param, and script elements. -->
<attribute name="lang"/>
</global-tag-attributes>
<tag-rules>
<!-- Tags related to JavaScript -->
<tag name="script" action="remove"/>
<tag name="noscript" action="validate"/> <!-- although no javascript can fire inside a noscript tag, css is still a viable attack vector -->
<!-- Frame & related tags -->
<tag name="iframe" action="remove"/>
<tag name="frameset" action="remove"/>
<tag name="frame" action="remove"/>
<!-- Form related tags -->
<tag name="label" action="validate">
<attribute name="for">
<regexp-list>
<regexp name="htmlId"/>
</regexp-list>
</attribute>
</tag>
<!-- All formatting tags -->
<tag name="h1" action="validate"/>
<tag name="h2" action="validate"/>
<tag name="h3" action="validate"/>
<tag name="h4" action="validate"/>
<tag name="h5" action="validate"/>
<tag name="h6" action="validate"/>
<tag name="p" action="validate">
<attribute name="align"/>
</tag>
<tag name="i" action="validate"/>
<tag name="b" action="validate"/>
<tag name="u" action="validate"/>
<tag name="strong" action="validate"/>
<tag name="em" action="validate"/>
<tag name="small" action="validate"/>
<tag name="big" action="validate"/>
<tag name="pre" action="validate"/>
<tag name="code" action="validate"/>
<tag name="cite" action="validate"/>
<tag name="samp" action="validate"/>
<tag name="sub" action="validate"/>
<tag name="sup" action="validate"/>
<tag name="strike" action="validate"/>
<tag name="center" action="validate"/>
<tag name="blockquote" action="validate"/>
<tag name="hr" action="validate"/>
<tag name="br" action="validate"/>
<!--tag name="col" action="validate"/-->
<tag name="font" action="validate">
<attribute name="color">
<regexp-list>
<regexp name="colorNameOrCode"/>
</regexp-list>
</attribute>
<attribute name="face">
<regexp-list>
<regexp value="[\w;, ]+"/>
</regexp-list>
</attribute>
<attribute name="size">
<regexp-list>
<regexp value="(\+|-){0,1}(\d)+"/>
</regexp-list>
</attribute>
</tag>
<!-- Anchor and anchor related tags -->
<tag name="a" action="validate">
<!-- onInvalid="filterTag" has been removed as per suggestion at OWASP SJ 2007 - just "name" is valid -->
<attribute name="href"/>
<attribute name="onFocus"/>
<attribute name="onBlur"/>
<attribute name="nohref">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="rel">
<literal-list>
<literal value="nofollow"/>
</literal-list>
</attribute>
<attribute name="name"/>
</tag>
<tag name="map" action="validate"/>
<!-- base tag removed per demo - this could be enabled with literal-list values you allow -->
<!--
<tag name="base" action="validate">
<attribute name="href"/>
</tag>
-->
<!-- Stylesheet Tags -->
<tag name="style" action="validate">
<attribute name="type">
<literal-list>
<literal value="text/css"/>
</literal-list>
</attribute>
<attribute name="media"/>
</tag>
<tag name="span" action="validate"/>
<tag name="div" action="validate">
<attribute name="align"/>
</tag>
<!-- <attribute name="id"/> what could an attacker do if they could overwrite an existing div definition? prolly something bad -->
<!-- <attribute name="class"/> what could an attacker do if they could specify any class in the namespace? prolly something bad -->
<!-- Image & image related tags -->
<tag name="img" action="validate">
<attribute name="src" onInvalid="removeTag">
<regexp-list>
<regexp name="onsiteURL"/>
<regexp name="offsiteURL"/>
</regexp-list>
</attribute>
<attribute name="name"/>
<attribute name="alt"/>
<attribute name="height"/>
<attribute name="width"/>
<attribute name="border"/>
<attribute name="align"/>
<attribute name="hspace">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="vspace">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
</tag>
<!-- no way to do this safely without hooking up the same code to @import to embed the remote stylesheet (malicious user could change offsite resource to be malicious after validation -->
<!-- <attribute name="href" onInvalid="removeTag"/> -->
<tag name="link" action="validate">
<!-- <attribute name="href" onInvalid="removeTag"/> -->
<attribute name="media"/>
<attribute name="type" onInvalid="removeTag">
<literal-list>
<literal value="text/css"/>
<literal value="application/rss+xml"/>
<literal value="image/x-icon"/>
</literal-list>
</attribute>
<attribute name="rel">
<literal-list>
<literal value="stylesheet"/>
<literal value="shortcut icon"/>
<literal value="search"/>
<literal value="copyright"/>
<literal value="top"/>
<literal value="alternate"/>
</literal-list>
</attribute>
</tag>
<!-- List tags -->
<tag name="ul" action="validate"/>
<tag name="ol" action="validate"/>
<tag name="li" action="validate"/>
<!-- Dictionary tags -->
<tag name="dd" action="truncate"/>
<tag name="dl" action="truncate"/>
<tag name="dt" action="truncate"/>
<!-- Table tags (tbody, thead, tfoot)-->
<tag name="thead" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="tbody" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="tfoot" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="table" action="validate">
<attribute name="height"/>
<attribute name="width"/>
<attribute name="border"/>
<attribute name="bgcolor"/>
<attribute name="cellpadding"/>
<attribute name="cellspacing"/>
<attribute name="background"/>
<attribute name="align"/>
<attribute name="noresize">
<literal-list>
<literal value="noresize"/>
<literal value=""/>
</literal-list>
</attribute>
</tag>
<tag name="td" action="validate">
<attribute name="background"/>
<attribute name="bgcolor"/>
<attribute name="abbrev"/>
<attribute name="axis"/>
<attribute name="headers"/>
<attribute name="scope"/>
<attribute name="nowrap"/>
<attribute name="height"/>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
<attribute name="colspan"/>
<attribute name="rowspan"/>
</tag>
<tag name="th" action="validate">
<attribute name="abbrev"/>
<attribute name="axis"/>
<attribute name="headers"/>
<attribute name="scope"/>
<attribute name="nowrap"/>
<attribute name="bgcolor"/>
<attribute name="height"/>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
<attribute name="colspan"/>
<attribute name="rowspan"/>
</tag>
<tag name="tr" action="validate">
<attribute name="height"/>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="valign"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="background"/>
</tag>
<tag name="colgroup" action="validate">
<attribute name="span">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="col" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
<attribute name="span">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="width"/>
</tag>
<tag name="fieldset" action="validate"/>
<tag name="legend" action="validate"/>
</tag-rules>
<!-- CSS validation processing rules -->
<css-rules>
<!--
<property name="counter-increment" default="none" description="The 'counter-increment' property accepts one or more names of counters (identifiers), each one optionally followed by an integer.">
<category-list>
<category value="all"/>
</category-list>
<literal-list>
<literal value="none"/>
<literal value="inherit"/>
</literal-list>
<regexp-list>
<regexp name="cssId"/>
<regexp name="integer"/>
</regexp-list>
</property>
-->
<property name="font-family" description="This property specifies a prioritized list of font family names and/or generic family names.">
<category-list>
<category value="visual"/>
</category-list>
<literal-list>
<literal value="serif"/>
<literal value="arial"/>
<literal value="lucida console"/>
<literal value="sans-serif"/>
<literal value="cursive"/>
<literal value="verdana"/>
<literal value="fantasy"/>
<literal value="monospace"/>
</literal-list>
<regexp-list>
<regexp value="[\w,\-&apos;&quot; ]+"/>
</regexp-list>
</property>
<property name="page" description="The 'page' property can be used to specify a particular type of page where an element should be displayed.">
<category-list>
<category value="visual"/>
<category value="paged"/>
</category-list>
<literal-list>
<literal value="auto"/>
</literal-list>
<regexp-list>
<regexp name="cssId"/>
</regexp-list>
</property>
</css-rules>
</anti-samy-rules>

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,154 @@
<?xml version="1.0" encoding="UTF-8"?>
<xsd:schema
xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="rules">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="directives" type="Directives" maxOccurs="1" minOccurs="1"/>
<xsd:element name="common-regexps" type="CommonRegexps" maxOccurs="1" minOccurs="1"/>
<xsd:element name="common-attributes" type="AttributeList" maxOccurs="1" minOccurs="1"/>
<xsd:element name="global-tag-attributes" type="AttributeList" maxOccurs="1" minOccurs="1"/>
<xsd:element name="tag-rules" type="TagRules" minOccurs="1" maxOccurs="1"/>
<xsd:element name="css-rules" type="CSSRules" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
<xsd:complexType name="Directives">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="directive" type="Directive" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Directive">
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="value" use="required"/>
</xsd:complexType>
<xsd:complexType name="CommonRegexps">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="regexp" type="RegExp" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="AttributeList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="attribute" type="Attribute" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="TagRules">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="tag" type="Tag" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Tag">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="attribute" type="Attribute" minOccurs="0" />
</xsd:sequence>
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="action" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="Remove" />
<xsd:enumeration value="Truncate" />
<xsd:enumeration value="Validate" />
<xsd:enumeration value="Filter" />
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="Attribute">
<xsd:sequence>
<xsd:element name="regexp-list" type="RegexpList" minOccurs="0"/>
<xsd:element name="literal-list" type="LiteralList" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="description"/>
<xsd:attribute name="onInvalid">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="RemoveAttribute" />
<xsd:enumeration value="RemoveTag" />
<xsd:enumeration value="FilterTag" />
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="RegexpList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="regexp" type="RegExp" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="RegExp">
<xsd:attribute name="name" type="xsd:string"/>
<xsd:attribute name="value" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="LiteralList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="literal" type="Literal" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Literal">
<xsd:attribute name="value" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CSSRules">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="property" type="Property" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Property">
<xsd:sequence>
<xsd:element name="category-list" type="CategoryList" minOccurs="0"/>
<xsd:element name="literal-list" type="LiteralList" minOccurs="0"/>
<xsd:element name="regexp-list" type="RegexpList" minOccurs="0"/>
<xsd:element name="shorthand-list" type="ShorthandList" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="default" type="xsd:string"/>
<xsd:attribute name="description" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="ShorthandList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="shorthand" type="Shorthand" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Shorthand">
<xsd:attribute name="name" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="CategoryList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="category" type="Category" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Category">
<xsd:attribute name="value" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="Entity">
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="cdata" type="xsd:string" use="required"/>
</xsd:complexType>
</xsd:schema>

View File

@@ -9,6 +9,7 @@ using AntiXssUF.TestSite.Models;
using Ufangx.Xss;
using System.Collections.Generic;
using System.Linq;
using System.Threading.Tasks;
namespace AntiXssUF.TestSite.Controllers
{
@@ -23,6 +24,11 @@ namespace AntiXssUF.TestSite.Controllers
_logger = logger;
this.policyFactory = policyFactory;
}
public async Task<IActionResult> Test(string source) {
var filter=await policyFactory.CreateHtmlFilter("ebay");
var clean = filter.Filters(source);
return Content(clean);
}
void FilterAttacks(RichText richText, Func<string, bool> fn, [CallerMemberName] string propertyName = null)
{
html.Append($"\n==== in {propertyName} ==================================================\n原文:\n{ HttpUtility.HtmlEncode(richText.Source)}\n");
@@ -167,7 +173,8 @@ namespace AntiXssUF.TestSite.Controllers
[HttpPost]
public IActionResult Test(TestModel model)
{
ViewBag.html = model?.RichText?.ToString();
var clean = model?.RichText?.ToString() ?? string.Empty;
ViewBag.html = clean;
return View();
}

View File

@@ -27,7 +27,7 @@ namespace AntiXssUF.TestSite
// This method gets called by the runtime. Use this method to add services to the container.
public void ConfigureServices(IServiceCollection services)
{
services.AddXssFilter(opt=>opt.DefaultSchemeName= "DefaultPolicy")
services.AddXssFilter(opt=>opt.DefaultSchemeName= "test")
.AddScheme<AntisamyPolicy>("antisamy", () => File.ReadAllTextAsync(Path.Combine(HostEnvironment.ContentRootPath, "resources/antisamy.xml")))
.AddScheme<AntisamyPolicy>("anythinggoes", () => File.ReadAllTextAsync(Path.Combine(HostEnvironment.ContentRootPath, "resources/antisamy-anythinggoes.xml")))
.AddScheme<AntisamyPolicy>("ebay", () => File.ReadAllTextAsync(Path.Combine(HostEnvironment.ContentRootPath, "resources/antisamy-ebay.xml")))

View File

@@ -98,7 +98,7 @@ http://www.w3.org/TR/html401/struct/global.html
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>

View File

@@ -93,7 +93,7 @@ http://www.w3.org/TR/html401/struct/global.html
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>

View File

@@ -93,7 +93,7 @@ http://www.w3.org/TR/html401/struct/global.html
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>

View File

@@ -94,7 +94,7 @@ http://www.w3.org/TR/html401/struct/global.html
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>

View File

@@ -96,7 +96,7 @@ http://www.w3.org/TR/html401/struct/global.html
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>

View File

@@ -96,7 +96,7 @@ http://www.w3.org/TR/html401/struct/global.html
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgb\(([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]),([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\)"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>

View File

@@ -4,6 +4,16 @@
<TargetFramework>netstandard2.1</TargetFramework>
<AssemblyName>AntiXssUF</AssemblyName>
<RootNamespace>Ufangx.Xss</RootNamespace>
<GeneratePackageOnBuild>true</GeneratePackageOnBuild>
<Description>xss anit policy filter</Description>
<Authors>Jackson.bruce</Authors>
<Company>ufangx</Company>
<Copyright>Copyright (c) 2020 Jackson.Bruce</Copyright>
<PackageProjectUrl>https://github.com/JacksonBruce/AntiXssUF</PackageProjectUrl>
<RepositoryUrl>https://github.com/JacksonBruce/AntiXssUF.git</RepositoryUrl>
<PackageTags>Anti Xss .NETStandard</PackageTags>
<PackageReleaseNotes>https://github.com/JacksonBruce/AntiXssUF/blob/master/README.md</PackageReleaseNotes>
<RepositoryType>git</RepositoryType>
</PropertyGroup>
<ItemGroup>

View File

@@ -0,0 +1,34 @@
<?xml version="1.0" encoding="utf-8"?>
<package xmlns="http://schemas.microsoft.com/packaging/2013/05/nuspec.xsd">
<metadata>
<id>$id$</id>
<version>$version$</version>
<authors>$author$</authors>
<owners>ufangx</owners>
<requireLicenseAcceptance>false</requireLicenseAcceptance>
<title>$title$</title>
<description>$author$</description>
<copyright>$copyright$</copyright>
<licenseUrl>https://github.com/JacksonBruce/AntiXssUF/blob/master/LICENSE</licenseUrl>
<projectUrl>https://github.com/JacksonBruce/AntiXssUF</projectUrl>
<releaseNotes>https://github.com/JacksonBruce/AntiXssUF/blob/master/README.md</releaseNotes>
<tags>Anti Xss .NETStandard </tags>
<repository url="https://github.com/JacksonBruce/AntiXssUF" />
<dependencies>
<group targetFramework=".NETStandard2.1">
<dependency id="AngleSharp" version="0.13.0" exclude="Build,Analyzers" />
<dependency id="AngleSharp.Css" version="0.13.0" exclude="Build,Analyzers" />
<dependency id="Microsoft.Extensions.Caching.Abstractions" version="3.1.2" exclude="Build,Analyzers" />
<dependency id="Microsoft.Extensions.Configuration.Binder" version="3.1.2" exclude="Build,Analyzers" />
<dependency id="Microsoft.Extensions.Configuration.Json" version="3.1.2" exclude="Build,Analyzers" />
<dependency id="Microsoft.Extensions.DependencyInjection" version="3.1.2" exclude="Build,Analyzers" />
<dependency id="Microsoft.Extensions.Options" version="3.1.2" exclude="Build,Analyzers" />
</group>
</dependencies>
</metadata>
<files>
<file src="netstandard2.1\*.dll" target="lib\netstandard2.1" />
<file src="resources\*.*" target="content\resources" />
</files>
</package>

View File

@@ -63,11 +63,11 @@ namespace Ufangx.Xss
});
Regex regex = new Regex($"^({Regex.Escape("<!doctype")})|({Regex.Escape("<html")})|({Regex.Escape("<body")})", RegexOptions.IgnoreCase);
var match = regex.Match(html);
var doc = match.Success ? htmlParser.ParseDocument(html) : htmlParser.ParseDocument("");
var doc = match.Success ? htmlParser.ParseDocument(html) : htmlParser.ParseDocument("<html><head></head><body></body></html>");
var container = match.Success ? doc.DocumentElement : doc.Body;
if (!match.Success) { container.InnerHtml = html; }
FiltersTags(container.ChildNodes);
return match.Success ? (match.Groups[3].Success ? doc.Body.OuterHtml : container.OuterHtml) : container.InnerHtml;
return container.HasChildNodes ? (match.Success ? (match.Groups[3].Success ? doc.Body?.OuterHtml : container.OuterHtml) : container.InnerHtml) : string.Empty;
}
#endregion

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,154 @@
<?xml version="1.0" encoding="UTF-8"?>
<xsd:schema
xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="rules">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="directives" type="Directives" maxOccurs="1" minOccurs="1"/>
<xsd:element name="common-regexps" type="CommonRegexps" maxOccurs="1" minOccurs="1"/>
<xsd:element name="common-attributes" type="AttributeList" maxOccurs="1" minOccurs="1"/>
<xsd:element name="global-tag-attributes" type="AttributeList" maxOccurs="1" minOccurs="1"/>
<xsd:element name="tag-rules" type="TagRules" minOccurs="1" maxOccurs="1"/>
<xsd:element name="css-rules" type="CSSRules" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
<xsd:complexType name="Directives">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="directive" type="Directive" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Directive">
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="value" use="required"/>
</xsd:complexType>
<xsd:complexType name="CommonRegexps">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="regexp" type="RegExp" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="AttributeList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="attribute" type="Attribute" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="TagRules">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="tag" type="Tag" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Tag">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="attribute" type="Attribute" minOccurs="0" />
</xsd:sequence>
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="action" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="Remove" />
<xsd:enumeration value="Truncate" />
<xsd:enumeration value="Validate" />
<xsd:enumeration value="Filter" />
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="Attribute">
<xsd:sequence>
<xsd:element name="regexp-list" type="RegexpList" minOccurs="0"/>
<xsd:element name="literal-list" type="LiteralList" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="description"/>
<xsd:attribute name="onInvalid">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="RemoveAttribute" />
<xsd:enumeration value="RemoveTag" />
<xsd:enumeration value="FilterTag" />
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="RegexpList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="regexp" type="RegExp" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="RegExp">
<xsd:attribute name="name" type="xsd:string"/>
<xsd:attribute name="value" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="LiteralList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="literal" type="Literal" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Literal">
<xsd:attribute name="value" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CSSRules">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="property" type="Property" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Property">
<xsd:sequence>
<xsd:element name="category-list" type="CategoryList" minOccurs="0"/>
<xsd:element name="literal-list" type="LiteralList" minOccurs="0"/>
<xsd:element name="regexp-list" type="RegexpList" minOccurs="0"/>
<xsd:element name="shorthand-list" type="ShorthandList" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="default" type="xsd:string"/>
<xsd:attribute name="description" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="ShorthandList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="shorthand" type="Shorthand" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Shorthand">
<xsd:attribute name="name" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="CategoryList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="category" type="Category" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Category">
<xsd:attribute name="value" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="Entity">
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="cdata" type="xsd:string" use="required"/>
</xsd:complexType>
</xsd:schema>

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,176 @@
<?xml version="1.0" encoding="ISO-8859-1"?>
<!--
W3C rules retrieved from:
http://www.w3.org/TR/html401/struct/global.html
-->
<!--
Slashdot allowed tags taken from "Reply" page:
<b> <i> <p> <br> <a> <ol> <ul> <li> <dl> <dt> <dd> <em> <strong> <tt> <blockquote> <div> <ecode> <quote>
-->
<anti-samy-rules xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="antisamy.xsd">
<directives>
<directive name="omitXmlDeclaration" value="true"/>
<directive name="omitDoctypeDeclaration" value="true"/>
<directive name="maxInputSize" value="5000"/>
<directive name="useXHTML" value="true"/>
<directive name="formatOutput" value="true"/>
<directive name="embedStyleSheets" value="false"/>
</directives>
<common-regexps>
<!--
From W3C:
This attribute assigns a class name or set of class names to an
element. Any number of elements may be assigned the same class
name or names. Multiple class names must be separated by white
space characters.
-->
<regexp name="htmlTitle" value="[\p{L}\p{N}\s-_',:\[\]!\./\\\(\)]*"/> <!-- force non-empty with a '+' at the end instead of '*' -->
<regexp name="onsiteURL" value="([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)"/>
<regexp name="offsiteURL" value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*"/>
</common-regexps>
<!--
Tag.name = a, b, div, body, etc.
Tag.action = filter: remove tags, but keep content, validate: keep content as long as it passes rules, remove: remove tag and contents
Attribute.name = id, class, href, align, width, etc.
Attribute.onInvalid = what to do when the attribute is invalid, e.g., remove the tag (removeTag), remove the attribute (removeAttribute), filter the tag (filterTag)
Attribute.description = What rules in English you want to tell the users they can have for this attribute. Include helpful things so they'll be able to tune their HTML
-->
<!--
Some attributes are common to all (or most) HTML tags. There aren't many that qualify for this. You have to make sure there's no
collisions between any of these attribute names with attribute names of other tags that are for different purposes.
-->
<common-attributes>
<attribute name="lang" description="The 'lang' attribute tells the browser what language the element's attribute values and content are written in">
<regexp-list>
<regexp value="[a-zA-Z]{2,20}"/>
</regexp-list>
</attribute>
<attribute name="title" description="The 'title' attribute provides text that shows up in a 'tooltip' when a user hovers their mouse over the element">
<regexp-list>
<regexp name="htmlTitle"/>
</regexp-list>
</attribute>
<attribute name="href" onInvalid="filterTag">
<regexp-list>
<regexp name="onsiteURL"/>
<regexp name="offsiteURL"/>
</regexp-list>
</attribute>
<attribute name="align" description="The 'align' attribute of an HTML element is a direction word, like 'left', 'right' or 'center'">
<literal-list>
<literal value="center"/>
<literal value="left"/>
<literal value="right"/>
<literal value="justify"/>
<literal value="char"/>
</literal-list>
</attribute>
</common-attributes>
<!--
This requires normal updates as browsers continue to diverge from the W3C and each other. As long as the browser wars continue
this is going to continue. I'm not sure war is the right word for what's going on. Doesn't somebody have to win a war after
a while?
-->
<global-tag-attributes>
<attribute name="title"/>
<attribute name="lang"/>
</global-tag-attributes>
<tag-rules>
<!-- Tags related to JavaScript -->
<tag name="script" action="remove"/>
<tag name="noscript" action="remove"/>
<!-- Frame & related tags -->
<tag name="iframe" action="remove"/>
<tag name="frameset" action="remove"/>
<tag name="frame" action="remove"/>
<tag name="noframes" action="remove"/>
<!-- CSS related tags -->
<tag name="style" action="remove"/>
<!-- All reasonable formatting tags -->
<tag name="p" action="validate">
<attribute name="align"/>
</tag>
<tag name="div" action="validate"/>
<tag name="i" action="validate"/>
<tag name="b" action="validate"/>
<tag name="em" action="validate"/>
<tag name="blockquote" action="validate"/>
<tag name="tt" action="validate"/>
<tag name="br" action="truncate"/>
<!-- Custom Slashdot tags, though we're trimming the idea of having a possible mismatching end tag with the endtag="" attribute -->
<tag name="quote" action="validate"/>
<tag name="ecode" action="validate"/>
<!-- Anchor and anchor related tags -->
<tag name="a" action="validate">
<attribute name="href" onInvalid="filterTag"/>
<attribute name="nohref">
<literal-list>
<literal value="nohref"/>
<literal value=""/>
</literal-list>
</attribute>
<attribute name="rel">
<literal-list>
<literal value="nofollow"/>
</literal-list>
</attribute>
</tag>
<!-- List tags -->
<tag name="ul" action="validate"/>
<tag name="ol" action="validate"/>
<tag name="li" action="validate"/>
</tag-rules>
<!-- No CSS on Slashdot posts -->
<css-rules>
</css-rules>
</anti-samy-rules>

View File

@@ -0,0 +1,862 @@
<?xml version="1.0" encoding="ISO-8859-1" ?>
<!--
W3C rules retrieved from:
http://www.w3.org/TR/html401/struct/global.html
-->
<anti-samy-rules xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="antisamy.xsd">
<directives>
<directive name="omitXmlDeclaration" value="true"/>
<directive name="omitDoctypeDeclaration" value="true"/>
<directive name="maxInputSize" value="20001"/>
<directive name="useXHTML" value="true"/>
<directive name="formatOutput" value="true"/>
<!--
remember, this won't work for relative URIs - AntiSamy doesn't
know anything about the URL or your web structure
-->
<directive name="embedStyleSheets" value="false"/>
</directives>
<common-regexps>
<!--
From W3C:
This attribute assigns a class name or set of class names to an
element. Any number of elements may be assigned the same class
name or names. Multiple class names must be separated by white
space characters.
-->
<regexp name="colorNameOrCode" value="(#[0-9a-fA-F]{6}|[a-zA-Z]{1,20})"/>
<regexp name="number" value="[0-9]+"/>
<regexp name="anything" value=".*"/>
<regexp name="numberOrPercent" value="(\d)+(%{0,1})"/>
<regexp name="paragraph" value="([\p{L}\p{N},'\.\s\-_\(\)]|&amp;[0-9]{2};)*"/>
<regexp name="htmlId" value="[a-zA-Z0-9-_]+"/>
<regexp name="htmlTitle" value="[\p{L}\p{N}\s-_',:\[\]!\./\\\(\)]*"/> <!-- force non-empty with a '+' at the end instead of '*' -->
<regexp name="htmlClass" value="[a-zA-Z0-9\s,-_]+"/>
<regexp name="onsiteURL" value="([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)"/>
<regexp name="offsiteURL" value="(\s)*((ht|f)tp(s?)://|mailto:)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*"/>
<regexp name="boolean" value="(true|false)"/>
<regexp name="singlePrintable" value="[a-zA-Z0-9]{1}"/> <!-- \w allows the '_' character -->
<!-- This is for elements (ex: elemName { ... }) -->
<regexp name="cssElementSelector" value="[a-zA-Z0-9\-_]+|\*"/>
<!-- This is to list out any element names that are *not* valid -->
<regexp name="cssElementExclusion" value=""/>
<!-- This if for classes (ex: .className { ... }) -->
<regexp name="cssClassSelector" value="\.[a-zA-Z0-9\-_]+"/>
<!-- This is to list out any class names that are *not* valid -->
<regexp name="cssClassExclusion" value=""/>
<!-- This is for ID selectors (ex: #myId { ... } -->
<regexp name="cssIDSelector" value="#[a-zA-Z0-9\-_]+"/>
<!-- This is for ID selectors (ex: #myId { ... } -->
<regexp name="cssId" value="#[a-zA-Z0-9\-_]+"/>
<!-- This is to list out any IDs that are *not* valid - FIXME: What should the default be to avoid div hijacking? *? -->
<regexp name="cssIDExclusion" value=""/>
<!-- This is for pseudo-element selector (ex. foo:pseudo-element { ... } -->
<regexp name="cssPseudoElementSelector" value=":[a-zA-Z0-9\-_]+"/>
<!-- This is to list out any psuedo-element names that are *not* valid -->
<regexp name="cssPsuedoElementExclusion" value=""/>
<!-- This is for attribute selectors (ex. foo[attr=value] { ... } -->
<regexp name="cssAttributeSelector" value="\[[a-zA-Z0-9-_]+((=|~=|\|=){1}[a-zA-Z0-9\-_]+){1}\]"/>
<!-- This is to list out any attribute names that are *not* valid -->
<regexp name="cssAttributeExclusion" value=""/>
<!-- This is for resources referenced from CSS (such as background images and other imported stylesheets) -->
<regexp name="cssOnsiteUri" value="url\(([\p{L}\p{N}\\/\.\?=\#&amp;;\-_~]+|\#(\w)+)\)"/>
<regexp name="cssOffsiteUri" value="url\((\s)*((ht|f)tp(s?)://)[\p{L}\p{N}]+[~\p{L}\p{N}\p{Zs}\-_\.@#$%&amp;;:,\?=/\+!]*(\s)*\)"/>
<!-- This is for comments within CSS (ex. /* comment */) -->
<regexp name="cssCommentText" value="[\p{L}\p{N}-_,\/\\\.\s\(\)!\?\=\$#%\^&amp;:\[\]&quot;']+"/>
<regexp name="integer" value="(-|\+)?[0-9]+"/>
<regexp name="number" value="(-|\+)?([0-9]+(.[0-9]+)?)"/>
<regexp name="angle" value="(-|\+)?([0-9]+(.[0-9]+)?)(deg|grads|rad)"/>
<regexp name="time" value="([0-9]+(.[0-9]+)?)(ms|s)"/>
<regexp name="frequency" value="([0-9]+(.[0-9]+)?)(hz|khz)"/>
<regexp name="length" value="((-|\+)?0|(-|\+)?([0-9]+(.[0-9]+)?)(em|ex|px|in|cm|mm|pt|pc))"/>
<regexp name="percentage" value="(-|\+)?([0-9]+(.[0-9]+)?)%"/>
<regexp name="cssColor" value="(aqua|black|blue|fuchsia|gray|grey|green|lime|maroon|navy|olive|purple|red|silver|teal|white|yellow)|(^#[0-9a-fA-F]{3,3}$)|(^#[0-9a-fA-F]{6,6}$)|rgba?\\(\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])\\s*,\\s*([1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])(\\s*,\\s*[1])?\\s*\\)"/>
<regexp name="absolute-size" value="(xx-small|x-small|small|medium|large|x-large|xx-large)"/>
<regexp name="relative-size" value="(larger|smaller)"/>
</common-regexps>
<!--
Tag.name = a, b, div, body, etc.
Tag.action = filter: remove tags, but keep content, validate: keep content as long as it passes rules, remove: remove tag and contents
Attribute.name = id, class, href, align, width, etc.
Attribute.onInvalid = what to do when the attribute is invalid, e.g., remove the tag (removeTag), remove the attribute (removeAttribute), filter the tag (filterTag)
Attribute.description = What rules in English you want to tell the users they can have for this attribute. Include helpful things so they'll be able to tune their HTML
-->
<!--
Some attributes are common to all (or most) HTML tags. There aren't many that qualify for this. You have to make sure there's no
collisions between any of these attribute names with attribute names of other tags that are for different purposes.
-->
<common-attributes>
<!-- Common to all HTML tags -->
<attribute name="id" description="The 'id' of any HTML attribute should not contain anything besides letters and numbers">
<regexp-list>
<regexp value="[a-zA-Z0-9_\-\:]+"/>
</regexp-list>
</attribute>
<attribute name="class" description="The 'class' of any HTML attribute is usually a single word, but it can also be a list of class names separated by spaces">
<regexp-list>
<regexp name="htmlClass"/>
</regexp-list>
</attribute>
<attribute name="lang" description="The 'lang' attribute tells the browser what language the element's attribute values and content are written in">
<regexp-list>
<regexp value="[a-zA-Z]{2,20}"/>
</regexp-list>
</attribute>
<attribute name="title" description="The 'title' attribute provides text that shows up in a 'tooltip' when a user hovers their mouse over the element">
<regexp-list>
<regexp name="htmlTitle"/>
</regexp-list>
</attribute>
<attribute name="alt" description="The 'alt' attribute provides alternative text to users when its visual representation is not available">
<regexp-list>
<regexp name="paragraph"/>
</regexp-list>
</attribute>
<!-- the "style" attribute will be validated by an inline stylesheet scanner, so no need to define anything here - i hate having to special case this but no other choice -->
<attribute name="style" description="The 'style' attribute provides the ability for users to change many attributes of the tag's contents using a strict syntax"/>
<attribute name="media">
<literal-list>
<literal value="screen"/>
<literal value="tty"/>
<literal value="tv"/>
<literal value="projection"/>
<literal value="handheld"/>
<literal value="print"/>
<literal value="braille"/>
<literal value="aural"/>
<literal value="all"/>
</literal-list>
</attribute>
<!-- Anchor related -->
<!-- onInvalid="filterTag" has been removed as per suggestion at OWASP SJ 2007 - just "name" is valid -->
<attribute name="href">
<regexp-list>
<regexp name="onsiteURL"/>
<regexp name="offsiteURL"/>
</regexp-list>
</attribute>
<attribute name="name">
<regexp-list>
<regexp value="[a-zA-Z0-9-_\$]+"/>
<!--
have to allow the $ for .NET controls - although,
will users be supplying input that has server-generated
.NET control names? methinks not, but i want to pass my
test cases
-->
</regexp-list>
</attribute>
<attribute name="shape" description="The 'shape' attribute defines the shape of the selectable area">
<literal-list>
<literal value="default"/>
<literal value="rect"/>
<literal value="circle"/>
<literal value="poly"/>
</literal-list>
</attribute>
<!-- Table attributes -->
<attribute name="border">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="cellpadding">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="cellspacing">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="colspan">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="rowspan">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="background">
<regexp-list>
<regexp name="onsiteURL"/>
</regexp-list>
</attribute>
<attribute name="bgcolor">
<regexp-list>
<regexp name="colorNameOrCode"/>
</regexp-list>
</attribute>
<attribute name="abbrev">
<regexp-list>
<regexp name="paragraph"/>
</regexp-list>
</attribute>
<attribute name="headers" description="The 'headers' attribute is a space-separated list of cell IDs">
<regexp-list>
<regexp value="[a-zA-Z0-9\s*]*"/>
</regexp-list>
</attribute>
<attribute name="charoff">
<regexp-list>
<regexp value="numberOrPercent"/>
</regexp-list>
</attribute>
<attribute name="char">
<regexp-list>
<regexp value=".*{0,1}"/>
</regexp-list>
</attribute>
<attribute name="axis" description="The 'headers' attribute is a comma-separated list of related header cells">
<regexp-list>
<regexp value="[a-zA-Z0-9\s*,]*"/>
</regexp-list>
</attribute>
<attribute name="nowrap" description="The 'nowrap' attribute tells the browser not to wrap text that goes over one line">
<regexp-list>
<regexp name="anything"/>
<!-- <regexp value="(nowrap){0,1}"/> -->
</regexp-list>
</attribute>
<!-- Common positioning attributes -->
<attribute name="width">
<regexp-list>
<regexp name="numberOrPercent"/>
</regexp-list>
</attribute>
<attribute name="height">
<regexp-list>
<regexp name="numberOrPercent"/>
</regexp-list>
</attribute>
<attribute name="align" description="The 'align' attribute of an HTML element is a direction word, like 'left', 'right' or 'center'">
<literal-list>
<literal value="center"/>
<literal value="middle"/>
<literal value="left"/>
<literal value="right"/>
<literal value="justify"/>
<literal value="char"/>
</literal-list>
</attribute>
<attribute name="valign" description="The 'valign' attribute of an HTML attribute is a direction word, like 'baseline','bottom','middle' or 'top'">
<literal-list>
<literal value="baseline"/>
<literal value="bottom"/>
<literal value="middle"/>
<literal value="top"/>
</literal-list>
</attribute>
<!-- Intrinsic JavaScript Events -->
<attribute name="onFocus" description="The 'onFocus' event is executed when the control associated with the tag gains focus">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onBlur" description="The 'onBlur' event is executed when the control associated with the tag loses focus">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onClick" description="The 'onClick' event is executed when the control associated with the tag is clicked">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onDblClick" description="The 'onDblClick' event is executed when the control associated with the tag is clicked twice immediately">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onMouseDown" description="The 'onMouseDown' event is executed when the control associated with the tag is clicked but not yet released">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onMouseUp" description="The 'onMouseUp' event is executed when the control associated with the tag is clicked after the button is released">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="onMouseOver" description="The 'onMouseOver' event is executed when the user's mouse hovers over the control associated with the tag">
<literal-list>
<literal value="javascript:void(0)"/>
<literal value="javascript:history.go(-1)"/>
</literal-list>
</attribute>
<attribute name="scope" description="The 'scope' attribute defines what's covered by the header cells">
<literal-list>
<literal value="row"/>
<literal value="col"/>
<literal value="rowgroup"/>
<literal value="colgroup"/>
</literal-list>
</attribute>
<!-- If you want users to be able to mess with tabindex, uncomment this -->
<!--
<attribute name="tabindex" description="...">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
-->
<!-- Input/form related common attributes -->
<attribute name="disabled">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="readonly">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="accesskey">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="size">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="autocomplete">
<literal-list>
<literal value="on"/>
<literal value="off"/>
</literal-list>
</attribute>
<attribute name="rows">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="cols">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
</common-attributes>
<!--
This requires normal updates as browsers continue to diverge from the W3C and each other. As long as the browser wars continue
this is going to continue. I'm not sure war is the right word for what's going on. Doesn't somebody have to win a war after
a while? Even wars of attrition, surely?
-->
<global-tag-attributes>
<!-- Not valid in base, head, html, meta, param, script, style, and title elements. -->
<attribute name="id"/>
<attribute name="style"/>
<attribute name="title"/>
<attribute name="class"/>
<!-- Not valid in base, br, frame, frameset, hr, iframe, param, and script elements. -->
<attribute name="lang"/>
</global-tag-attributes>
<tag-rules>
<!-- Tags related to JavaScript -->
<tag name="script" action="remove"/>
<tag name="noscript" action="validate"/> <!-- although no javascript can fire inside a noscript tag, css is still a viable attack vector -->
<!-- Frame & related tags -->
<tag name="iframe" action="remove"/>
<tag name="frameset" action="remove"/>
<tag name="frame" action="remove"/>
<!-- Form related tags -->
<tag name="label" action="validate">
<attribute name="for">
<regexp-list>
<regexp name="htmlId"/>
</regexp-list>
</attribute>
</tag>
<!-- All formatting tags -->
<tag name="h1" action="validate"/>
<tag name="h2" action="validate"/>
<tag name="h3" action="validate"/>
<tag name="h4" action="validate"/>
<tag name="h5" action="validate"/>
<tag name="h6" action="validate"/>
<tag name="p" action="validate">
<attribute name="align"/>
</tag>
<tag name="i" action="validate"/>
<tag name="b" action="validate"/>
<tag name="u" action="validate"/>
<tag name="strong" action="validate"/>
<tag name="em" action="validate"/>
<tag name="small" action="validate"/>
<tag name="big" action="validate"/>
<tag name="pre" action="validate"/>
<tag name="code" action="validate"/>
<tag name="cite" action="validate"/>
<tag name="samp" action="validate"/>
<tag name="sub" action="validate"/>
<tag name="sup" action="validate"/>
<tag name="strike" action="validate"/>
<tag name="center" action="validate"/>
<tag name="blockquote" action="validate"/>
<tag name="hr" action="validate"/>
<tag name="br" action="validate"/>
<!--tag name="col" action="validate"/-->
<tag name="font" action="validate">
<attribute name="color">
<regexp-list>
<regexp name="colorNameOrCode"/>
</regexp-list>
</attribute>
<attribute name="face">
<regexp-list>
<regexp value="[\w;, ]+"/>
</regexp-list>
</attribute>
<attribute name="size">
<regexp-list>
<regexp value="(\+|-){0,1}(\d)+"/>
</regexp-list>
</attribute>
</tag>
<!-- Anchor and anchor related tags -->
<tag name="a" action="validate">
<!-- onInvalid="filterTag" has been removed as per suggestion at OWASP SJ 2007 - just "name" is valid -->
<attribute name="href"/>
<attribute name="onFocus"/>
<attribute name="onBlur"/>
<attribute name="nohref">
<regexp-list>
<regexp name="anything"/>
</regexp-list>
</attribute>
<attribute name="rel">
<literal-list>
<literal value="nofollow"/>
</literal-list>
</attribute>
<attribute name="name"/>
</tag>
<tag name="map" action="validate"/>
<!-- base tag removed per demo - this could be enabled with literal-list values you allow -->
<!--
<tag name="base" action="validate">
<attribute name="href"/>
</tag>
-->
<!-- Stylesheet Tags -->
<tag name="style" action="validate">
<attribute name="type">
<literal-list>
<literal value="text/css"/>
</literal-list>
</attribute>
<attribute name="media"/>
</tag>
<tag name="span" action="validate"/>
<tag name="div" action="validate">
<attribute name="align"/>
</tag>
<!-- <attribute name="id"/> what could an attacker do if they could overwrite an existing div definition? prolly something bad -->
<!-- <attribute name="class"/> what could an attacker do if they could specify any class in the namespace? prolly something bad -->
<!-- Image & image related tags -->
<tag name="img" action="validate">
<attribute name="src" onInvalid="removeTag">
<regexp-list>
<regexp name="onsiteURL"/>
<regexp name="offsiteURL"/>
</regexp-list>
</attribute>
<attribute name="name"/>
<attribute name="alt"/>
<attribute name="height"/>
<attribute name="width"/>
<attribute name="border"/>
<attribute name="align"/>
<attribute name="hspace">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="vspace">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
</tag>
<!-- no way to do this safely without hooking up the same code to @import to embed the remote stylesheet (malicious user could change offsite resource to be malicious after validation -->
<!-- <attribute name="href" onInvalid="removeTag"/> -->
<tag name="link" action="validate">
<!-- <attribute name="href" onInvalid="removeTag"/> -->
<attribute name="media"/>
<attribute name="type" onInvalid="removeTag">
<literal-list>
<literal value="text/css"/>
<literal value="application/rss+xml"/>
<literal value="image/x-icon"/>
</literal-list>
</attribute>
<attribute name="rel">
<literal-list>
<literal value="stylesheet"/>
<literal value="shortcut icon"/>
<literal value="search"/>
<literal value="copyright"/>
<literal value="top"/>
<literal value="alternate"/>
</literal-list>
</attribute>
</tag>
<!-- List tags -->
<tag name="ul" action="validate"/>
<tag name="ol" action="validate"/>
<tag name="li" action="validate"/>
<!-- Dictionary tags -->
<tag name="dd" action="truncate"/>
<tag name="dl" action="truncate"/>
<tag name="dt" action="truncate"/>
<!-- Table tags (tbody, thead, tfoot)-->
<tag name="thead" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="tbody" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="tfoot" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="table" action="validate">
<attribute name="height"/>
<attribute name="width"/>
<attribute name="border"/>
<attribute name="bgcolor"/>
<attribute name="cellpadding"/>
<attribute name="cellspacing"/>
<attribute name="background"/>
<attribute name="align"/>
<attribute name="noresize">
<literal-list>
<literal value="noresize"/>
<literal value=""/>
</literal-list>
</attribute>
</tag>
<tag name="td" action="validate">
<attribute name="background"/>
<attribute name="bgcolor"/>
<attribute name="abbrev"/>
<attribute name="axis"/>
<attribute name="headers"/>
<attribute name="scope"/>
<attribute name="nowrap"/>
<attribute name="height"/>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
<attribute name="colspan"/>
<attribute name="rowspan"/>
</tag>
<tag name="th" action="validate">
<attribute name="abbrev"/>
<attribute name="axis"/>
<attribute name="headers"/>
<attribute name="scope"/>
<attribute name="nowrap"/>
<attribute name="bgcolor"/>
<attribute name="height"/>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
<attribute name="colspan"/>
<attribute name="rowspan"/>
</tag>
<tag name="tr" action="validate">
<attribute name="height"/>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="valign"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="background"/>
</tag>
<tag name="colgroup" action="validate">
<attribute name="span">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="width"/>
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
</tag>
<tag name="col" action="validate">
<attribute name="align"/>
<attribute name="char"/>
<attribute name="charoff"/>
<attribute name="valign"/>
<attribute name="span">
<regexp-list>
<regexp name="number"/>
</regexp-list>
</attribute>
<attribute name="width"/>
</tag>
<tag name="fieldset" action="validate"/>
<tag name="legend" action="validate"/>
</tag-rules>
<!-- CSS validation processing rules -->
<css-rules>
<!--
<property name="counter-increment" default="none" description="The 'counter-increment' property accepts one or more names of counters (identifiers), each one optionally followed by an integer.">
<category-list>
<category value="all"/>
</category-list>
<literal-list>
<literal value="none"/>
<literal value="inherit"/>
</literal-list>
<regexp-list>
<regexp name="cssId"/>
<regexp name="integer"/>
</regexp-list>
</property>
-->
<property name="font-family" description="This property specifies a prioritized list of font family names and/or generic family names.">
<category-list>
<category value="visual"/>
</category-list>
<literal-list>
<literal value="serif"/>
<literal value="arial"/>
<literal value="lucida console"/>
<literal value="sans-serif"/>
<literal value="cursive"/>
<literal value="verdana"/>
<literal value="fantasy"/>
<literal value="monospace"/>
</literal-list>
<regexp-list>
<regexp value="[\w,\-&apos;&quot; ]+"/>
</regexp-list>
</property>
<property name="page" description="The 'page' property can be used to specify a particular type of page where an element should be displayed.">
<category-list>
<category value="visual"/>
<category value="paged"/>
</category-list>
<literal-list>
<literal value="auto"/>
</literal-list>
<regexp-list>
<regexp name="cssId"/>
</regexp-list>
</property>
</css-rules>
</anti-samy-rules>

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,137 @@
<?xml version="1.0" encoding="UTF-8"?>
<xsd:schema
xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="anti-samy-rules">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="directives" type="Directives" maxOccurs="1" minOccurs="1"/>
<xsd:element name="common-regexps" type="CommonRegexps" maxOccurs="1" minOccurs="1"/>
<xsd:element name="common-attributes" type="AttributeList" maxOccurs="1" minOccurs="1"/>
<xsd:element name="global-tag-attributes" type="AttributeList" maxOccurs="1" minOccurs="1"/>
<xsd:element name="tag-rules" type="TagRules" minOccurs="1" maxOccurs="1"/>
<xsd:element name="css-rules" type="CSSRules" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
<xsd:complexType name="Directives">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="directive" type="Directive" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Directive">
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="value" use="required"/>
</xsd:complexType>
<xsd:complexType name="CommonRegexps">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="regexp" type="RegExp" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="AttributeList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="attribute" type="Attribute" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="TagRules">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="tag" type="Tag" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Tag">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="attribute" type="Attribute" minOccurs="0" />
</xsd:sequence>
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="action" use="required"/>
</xsd:complexType>
<xsd:complexType name="Attribute">
<xsd:sequence>
<xsd:element name="regexp-list" type="RegexpList" minOccurs="0"/>
<xsd:element name="literal-list" type="LiteralList" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="name" use="required"/>
<xsd:attribute name="description"/>
<xsd:attribute name="onInvalid"/>
</xsd:complexType>
<xsd:complexType name="RegexpList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="regexp" type="RegExp" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="RegExp">
<xsd:attribute name="name" type="xsd:string"/>
<xsd:attribute name="value" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="LiteralList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="literal" type="Literal" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Literal">
<xsd:attribute name="value" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CSSRules">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="property" type="Property" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Property">
<xsd:sequence>
<xsd:element name="category-list" type="CategoryList" minOccurs="0"/>
<xsd:element name="literal-list" type="LiteralList" minOccurs="0"/>
<xsd:element name="regexp-list" type="RegexpList" minOccurs="0"/>
<xsd:element name="shorthand-list" type="ShorthandList" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="default" type="xsd:string"/>
<xsd:attribute name="description" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="ShorthandList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="shorthand" type="Shorthand" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Shorthand">
<xsd:attribute name="name" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="CategoryList">
<xsd:sequence maxOccurs="unbounded">
<xsd:element name="category" type="Category" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="Category">
<xsd:attribute name="value" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="Entity">
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="cdata" type="xsd:string" use="required"/>
</xsd:complexType>
</xsd:schema>