Sanitize hardening (#1504)

Sanitize hardening

Co-authored-by: Tony Brix <tony@brix.ninja>

README.md

@@ -39,7 +39,7 @@ Also read about:
 
 ## Usage
 
-### Warning: 🚨 Marked does not [sanitize](https://marked.js.org/#/USING_ADVANCED.md#options) the output HTML by default 🚨
+### Warning: 🚨 Marked does not [sanitize](https://marked.js.org/#/USING_ADVANCED.md#options) the output HTML. Please use a sanitize library, like [DOMPurify](https://github.com/cure53/DOMPurify) (recommended), [sanitize-html](https://github.com/apostrophecms/sanitize-html) or [insane](https://github.com/bevacqua/insane) on the output HTML! 🚨
 
 **CLI**
 

docs/README.md

@@ -25,7 +25,7 @@ These documentation pages are also rendered using marked 💯
 
 <h2 id="usage">Usage</h2>
 
-### Warning: 🚨 Marked does not [sanitize](https://marked.js.org/#/USING_ADVANCED.md#options) the output HTML by default 🚨
+### Warning: 🚨 Marked does not [sanitize](https://marked.js.org/#/USING_ADVANCED.md#options) the output HTML. Please use a sanitize library, like [DOMPurify](https://github.com/cure53/DOMPurify) (recommended), [sanitize-html](https://github.com/apostrophecms/sanitize-html) or [insane](https://github.com/bevacqua/insane) on the output HTML! 🚨
 
 **CLI**
 

docs/USING_ADVANCED.md

@@ -51,7 +51,7 @@ console.log(marked(markdownString));
 |mangle      |`boolean` |`true`   |v0.3.4   |If true, autolinked email address is escaped with HTML character references.|
 |pedantic    |`boolean` |`false`  |v0.2.1   |If true, conform to the original `markdown.pl` as much as possible. Don't fix original markdown bugs or behavior. Turns off and overrides `gfm`.|
 |renderer    |`object`  |`new Renderer()`|v0.3.0|An object containing functions to render tokens to HTML. See [extensibility](USING_PRO.md) for more details.|
-|sanitize    |`boolean` |`false`  |v0.2.1   |If true, sanitize the HTML passed into `markdownString` with the `sanitizer` function.|
+|sanitize    |`boolean` |`false`  |v0.2.1   |If true, sanitize the HTML passed into `markdownString` with the `sanitizer` function.<br>**Warning**: This feature is deprecated and it should NOT be used as it cannot be considered secure.<br>Instead use a sanitize library, like [DOMPurify](https://github.com/cure53/DOMPurify) (recommended), [sanitize-html](https://github.com/apostrophecms/sanitize-html) or [insane](https://github.com/bevacqua/insane) on the output HTML! |
 |sanitizer   |`function`|`null`   |v0.3.4   |A function to sanitize the HTML passed into `markdownString`.|
 |silent      |`boolean` |`false`  |v0.2.7   |If true, the parser does not throw any exception.|
 |smartLists  |`boolean` |`false`  |v0.2.8   |If true, use smarter list behavior than those found in `markdown.pl`.|

lib/marked.js

@@ -434,7 +434,7 @@ Lexer.prototype.token = function(src, top) {
           : 'html',
         pre: !this.options.sanitizer
           && (cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style'),
-        text: cap[0]
+        text: this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]
       });
       continue;
     }
@@ -850,7 +850,7 @@ InlineLexer.prototype.output = function(src) {
     if (cap = this.rules.text.exec(src)) {
       src = src.substring(cap[0].length);
       if (this.inRawBlock) {
-        out += this.renderer.text(cap[0]);
+        out += this.renderer.text(this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]);
       } else {
         out += this.renderer.text(escape(this.smartypants(cap[0])));
       }
@@ -1539,6 +1539,12 @@ function findClosingBracket(str, b) {
   return -1;
 }
 
+function checkSanitizeDeprecation(opt) {
+  if (opt && opt.sanitize && !opt.silent) {
+    console.warn('marked(): sanitize and sanitizer parameters are deprecated since version 0.7.0, should not be used and will be removed in the future. Read more here: https://marked.js.org/#/USING_ADVANCED.md#options');
+  }
+}
+
 /**
  * Marked
  */
@@ -1560,6 +1566,7 @@ function marked(src, opt, callback) {
     }
 
     opt = merge({}, marked.defaults, opt || {});
+    checkSanitizeDeprecation(opt);
 
     var highlight = opt.highlight,
         tokens,
@@ -1624,6 +1631,7 @@ function marked(src, opt, callback) {
   }
   try {
     if (opt) opt = merge({}, marked.defaults, opt);
+    checkSanitizeDeprecation(opt);
     return Parser.parse(Lexer.lex(src, opt), opt);
   } catch (e) {
     e.message += '\nPlease report this to https://github.com/markedjs/marked.';

test/specs/run-spec.js

@@ -16,6 +16,10 @@ function runSpecs(title, dir, showCompletionTable, options) {
           spec.options = Object.assign({}, options, (spec.options || {}));
           const example = (spec.example ? ' example ' + spec.example : '');
           const passFail = (spec.shouldFail ? 'fail' : 'pass');
+          if (spec.options.sanitizer) {
+            // eslint-disable-next-line no-eval
+            spec.options.sanitizer = eval(spec.options.sanitizer);
+          }
           (spec.only ? fit : it)('should ' + passFail + example, () => {
             const before = process.hrtime();
             if (spec.shouldFail) {
@@ -40,3 +44,4 @@ runSpecs('CommonMark', './commonmark', true, { headerIds: false });
 runSpecs('Original', './original', false, { gfm: false });
 runSpecs('New', './new');
 runSpecs('ReDOS', './redos');
+runSpecs('Security', './security', false, { silent: true }); // silent - do not show deprecation warning

test/specs/security/sanitizer_bypass.html

@@ -0,0 +1,6 @@
+<p>AAA&lt;script&gt; &lt;img &lt;script&gt; src=x onerror=alert(1) /&gt;BBB</p>
+
+<p>AAA&lt;sometag&gt; &lt;img &lt;sometag&gt; src=x onerror=alert(1)BBB</p>
+
+<p>&lt;a&gt;a2&lt;a2t&gt;a2&lt;/a&gt; b &lt;c&gt;c&lt;/c&gt; d</p>
+<h1 id="text"><img src="URL" alt="text"></h1>

test/specs/security/sanitizer_bypass.md

@@ -0,0 +1,9 @@
+---
+sanitize: true
+---
+AAA<script> <img <script> src=x onerror=alert(1) />BBB
+
+AAA<sometag> <img <sometag> src=x onerror=alert(1)BBB
+
+<a>a2<a2t>a2</a> b <c>c</c> d
+# ![text](URL)

test/specs/security/sanitizer_bypass_remove_generic.html

@@ -0,0 +1,2 @@
+<p>a2a2 b c d</p>
+<h1 id="text"><img src="URL" alt="text"></h1>

test/specs/security/sanitizer_bypass_remove_generic.md

@@ -0,0 +1,6 @@
+---
+sanitize: true
+sanitizer: () => ''
+---
+<a>a2<a2t>a2</a> b <c>c</c> d
+# ![text](URL)

test/specs/security/sanitizer_bypass_remove_script.html

@@ -0,0 +1 @@
+<p>AAA</p>

test/specs/security/sanitizer_bypass_remove_script.md

@@ -0,0 +1,5 @@
+---
+sanitize: true
+sanitizer: () => ''
+---
+AAA<script> <img <script> src=x onerror=alert(1) />BBB

test/specs/security/sanitizer_bypass_remove_tag.html

@@ -0,0 +1 @@
+<p>AAA &lt;img  src=x onerror=alert(1)BBB</p>

test/specs/security/sanitizer_bypass_remove_tag.md

@@ -0,0 +1,5 @@
+---
+sanitize: true
+sanitizer: () => ''
+---
+AAA<sometag> <img <sometag> src=x onerror=alert(1)BBB