Replace markdown denylist sanitizer with vendored DOMPurify (mXSS hardening)

The previous _sanitizeHtml was a denylist over agent/transcript markdown
rendered via innerHTML; it missed style attributes and the svg/math mXSS
namespaces — e.g. <svg><style><img src=x onerror=alert(1)></style></svg>
re-serialized into a live <img onerror>.

Vendor DOMPurify 3.4.8 (allowlist) following the existing marked.min.js
vendor pattern (same-origin, CSP script-src 'self'; not in package.json so
no lockfile drift). New sanitize-html.js wires a hardened allowlist config
(FORBID style/svg/math/script/iframe/object/embed/form; no data attrs);
app.js _sanitizeHtml delegates to it with a fail-closed escape-all fallback.
index.html loads dompurify -> sanitize-html -> app.js (defer); build.mjs
minifies + content-hashes sanitize-html.js.

Test: test/markdown-sanitizer.test.ts (jsdom, real shipping artifacts) —
mXSS payloads neutralized + legit markdown preserved.

src/web/public/app.js

@@ -1302,28 +1302,14 @@ class CodemanApp {
 
   /** Strip dangerous elements and attributes from HTML (XSS prevention) */
   _sanitizeHtml(html) {
-    const tpl = document.createElement('template');
-    tpl.innerHTML = html;
-    const frag = tpl.content;
-    for (const el of frag.querySelectorAll('script, iframe, object, embed, form, base, meta, link, style')) {
-      el.remove();
+    if (typeof window !== 'undefined' && typeof window.sanitizeMarkdownHtml === 'function') {
+      return window.sanitizeMarkdownHtml(html);
     }
-    for (const el of frag.querySelectorAll('*')) {
-      for (const attr of [...el.attributes]) {
-        const name = attr.name.toLowerCase();
-        if (name.startsWith('on')) {
-          el.removeAttribute(attr.name);
-        } else if (['href', 'src', 'action', 'xlink:href', 'formaction'].includes(name)) {
-          const val = attr.value.replace(/\s/g, '').toLowerCase();
-          if (val.startsWith('javascript:') || val.startsWith('vbscript:') || val.startsWith('data:text/html')) {
-            el.removeAttribute(attr.name);
-          }
-        }
-      }
-    }
-    const div = document.createElement('div');
-    div.appendChild(frag);
-    return div.innerHTML;
+    // Fail closed: DOMPurify unavailable — never return un-sanitized HTML.
+    return String(html == null ? '' : html)
+      .replace(/&/g, '&')
+      .replace(/</g, '&lt;')
+      .replace(/>/g, '&gt;');
   }
 
   /**

src/web/public/index.html

@@ -39,6 +39,9 @@
   <script defer src="vendor/xterm-addon-unicode11.min.js"></script>
   <script defer src="vendor/xterm-zerolag-input.js"></script>
   <script defer src="vendor/marked.min.js"></script>
+  <!-- DOMPurify (allowlist HTML sanitizer for rendered markdown).
+       Must load before sanitize-html.js (which wires it) and app.js (which calls it). -->
+  <script defer src="vendor/dompurify.min.js"></script>
   <!-- Synchronous mobile detection — runs before first paint to prevent panel flash -->
   <script>if(window.innerWidth<768||(('ontouchstart' in window||navigator.maxTouchPoints>0)&&window.innerWidth<1024))document.documentElement.classList.add('mobile-init');</script>
   <!-- Synchronous skin selection — runs before first paint to prevent theme flash -->
@@ -1907,6 +1910,8 @@
   <script defer src="notification-manager.js"></script>
   <script defer src="keyboard-accessory.js"></script>
   <script defer src="input-cjk.js"></script>
+  <!-- Hardened markdown HTML sanitizer (wires DOMPurify). Must precede app.js. -->
+  <script defer src="sanitize-html.js"></script>
   <script defer src="app.js"></script>
   <script defer src="terminal-ui.js"></script>
   <script defer src="respawn-ui.js"></script>

src/web/public/sanitize-html.js

@@ -0,0 +1,159 @@
+/**
+ * @fileoverview Allowlist-based HTML sanitizer for markdown-rendered, agent/transcript-derived
+ * content that is subsequently assigned via innerHTML (response viewer, attachment markdown
+ * preview, message bodies).
+ *
+ * Security (COD-56): the previous sanitizer was a hand-rolled DENYLIST — it removed a fixed
+ * set of tags (script/iframe/object/embed/form/base/meta/link/style), stripped on* attrs and a
+ * few dangerous URL schemes, then re-serialized. Denylists are mXSS-prone: they did not strip
+ * `svg`/`math` (which carry their own foreign-namespace parsing rules and can smuggle script via
+ * namespace confusion), did not strip `style` attributes (CSS `expression()`/`url(javascript:)`
+ * on legacy engines), and had no positive allowlist, so any tag/attribute not explicitly named
+ * survived. `marked` runs with raw-HTML passthrough, so crafted HTML echoed by an agent flows
+ * straight into this function.
+ *
+ * This module replaces that with DOMPurify (Cure53), an allowlist sanitizer that is the
+ * industry standard for mXSS defense. It is configured to allow exactly the tag/attribute set
+ * that markdown rendering legitimately produces (headings, lists, code, blockquotes, links,
+ * tables, images with safe src) and to FORBID `style`/`svg`/`math` plus all event handlers and
+ * dangerous URL schemes.
+ *
+ * Cross-environment: in the browser this file runs as a classic <script> after
+ * vendor/dompurify.min.js and wires `window.sanitizeMarkdownHtml`. The factory is also exported
+ * (window/globalThis + CommonJS) so a jsdom unit test can build a sanitizer bound to a
+ * jsdom-window DOMPurify instance and exercise the exact same config.
+ *
+ * @globals {function} sanitizeMarkdownHtml - (html:string) => string, sanitized HTML
+ * @globals {function} createMarkdownSanitizer - (DOMPurify) => sanitizeMarkdownHtml (for tests)
+ * @dependency vendor/dompurify.min.js (provides the global DOMPurify)
+ * @loadorder 5.6 of 15 — after input-cjk.js(5.5), before app.js(6) (app.js calls it)
+ */
+
+(function (root) {
+  'use strict';
+
+  /**
+   * Tags markdown rendering (marked, gfm) legitimately emits. Anything outside this set is
+   * dropped by DOMPurify. Deliberately excludes svg/math (mXSS foreign-namespace vectors) and
+   * form/embed/object/iframe/script/style (no place in rendered markdown).
+   */
+  var ALLOWED_TAGS = [
+    'a',
+    'b',
+    'blockquote',
+    'br',
+    'caption',
+    'code',
+    'del',
+    'div',
+    'em',
+    'h1',
+    'h2',
+    'h3',
+    'h4',
+    'h5',
+    'h6',
+    'hr',
+    'i',
+    'img',
+    'ins',
+    'kbd',
+    'li',
+    'mark',
+    'ol',
+    'p',
+    'pre',
+    'q',
+    's',
+    'samp',
+    'span',
+    'strong',
+    'sub',
+    'sup',
+    'table',
+    'tbody',
+    'td',
+    'tfoot',
+    'th',
+    'thead',
+    'tr',
+    'ul',
+    'var',
+  ];
+
+  /**
+   * Attributes allowed on the tags above. `style` is intentionally absent (CSS-based vectors).
+   * `class`/`id` survive because the response viewer adds wrapper classes downstream and code
+   * blocks may carry `language-*` classes from marked.
+   */
+  var ALLOWED_ATTR = [
+    'href',
+    'src',
+    'alt',
+    'title',
+    'class',
+    'id',
+    'name',
+    'colspan',
+    'rowspan',
+    'align',
+    'width',
+    'height',
+    'lang',
+    'dir',
+    'start',
+    'reversed',
+    'type',
+  ];
+
+  /**
+   * Build a sanitizer bound to a specific DOMPurify instance. The browser passes the global
+   * DOMPurify; tests pass a jsdom-window-bound instance so the same config is exercised under
+   * vitest without a real browser.
+   */
+  function createMarkdownSanitizer(DOMPurify) {
+    if (!DOMPurify || typeof DOMPurify.sanitize !== 'function') {
+      throw new Error('createMarkdownSanitizer: a DOMPurify instance is required');
+    }
+
+    var CONFIG = {
+      ALLOWED_TAGS: ALLOWED_TAGS,
+      ALLOWED_ATTR: ALLOWED_ATTR,
+      // Defense in depth even though style/svg/math are not in ALLOWED_TAGS: also forbid the
+      // foreign-namespace roots and style so config drift can't silently re-admit them.
+      FORBID_TAGS: ['style', 'svg', 'math', 'script', 'iframe', 'object', 'embed', 'form'],
+      FORBID_ATTR: ['style'],
+      // No data: URIs except images; block the rest. SVG/MathML namespaces fully disabled.
+      USE_PROFILES: { html: true },
+      ALLOW_DATA_ATTR: false,
+      ADD_ATTR: [],
+      RETURN_DOM: false,
+      RETURN_DOM_FRAGMENT: false,
+      // Keep text content of any removed element (so stripping a stray tag doesn't eat prose),
+      // matching the previous serializer's behavior of dropping the element but not its text.
+      KEEP_CONTENT: true,
+    };
+
+    return function sanitizeMarkdownHtml(html) {
+      return DOMPurify.sanitize(html == null ? '' : String(html), CONFIG);
+    };
+  }
+
+  // Expose the factory for tests (and any non-browser consumer).
+  if (root) {
+    root.createMarkdownSanitizer = createMarkdownSanitizer;
+    // In the browser, vendor/dompurify.min.js has already defined the global DOMPurify.
+    if (root.DOMPurify && typeof root.DOMPurify.sanitize === 'function') {
+      root.sanitizeMarkdownHtml = createMarkdownSanitizer(root.DOMPurify);
+    }
+  }
+
+  // CommonJS export for the vitest/jsdom unit test.
+  if (typeof module !== 'undefined' && module.exports) {
+    module.exports = {
+      createMarkdownSanitizer: createMarkdownSanitizer,
+      ALLOWED_TAGS: ALLOWED_TAGS,
+      ALLOWED_ATTR: ALLOWED_ATTR,
+    };
+  }
+})(typeof globalThis !== 'undefined' ? globalThis : typeof window !== 'undefined' ? window : this);

src/web/public/vendor/dompurify.min.js

@@ -0,0 +1,3 @@
+/*! @license DOMPurify 3.4.8 | (c) Cure53 and other contributors | Released under the Apache license 2.0 and Mozilla Public License 2.0 | github.com/cure53/DOMPurify/blob/3.4.8/LICENSE */
+!function(e,t){"object"==typeof exports&&"undefined"!=typeof module?module.exports=t():"function"==typeof define&&define.amd?define(t):(e="undefined"!=typeof globalThis?globalThis:e||self).DOMPurify=t()}(this,function(){"use strict";function e(e,t){(null==t||t>e.length)&&(t=e.length);for(var n=0,o=Array(t);n<t;n++)o[n]=e[n];return o}function t(t,n){return function(e){if(Array.isArray(e))return e}(t)||function(e,t){var n=null==e?null:"undefined"!=typeof Symbol&&e[Symbol.iterator]||e["@@iterator"];if(null!=n){var o,r,i,a,l=[],c=!0,s=!1;try{if(i=(n=n.call(e)).next,0===t);else for(;!(c=(o=i.call(n)).done)&&(l.push(o.value),l.length!==t);c=!0);}catch(e){s=!0,r=e}finally{try{if(!c&&null!=n.return&&(a=n.return(),Object(a)!==a))return}finally{if(s)throw r}}return l}}(t,n)||function(t,n){if(t){if("string"==typeof t)return e(t,n);var o={}.toString.call(t).slice(8,-1);return"Object"===o&&t.constructor&&(o=t.constructor.name),"Map"===o||"Set"===o?Array.from(t):"Arguments"===o||/^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(o)?e(t,n):void 0}}(t,n)||function(){throw new TypeError("Invalid attempt to destructure non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method.")}()}const n=Object.entries,o=Object.setPrototypeOf,r=Object.isFrozen,i=Object.getPrototypeOf,a=Object.getOwnPropertyDescriptor;let l=Object.freeze,c=Object.seal,s=Object.create,u="undefined"!=typeof Reflect&&Reflect,f=u.apply,m=u.construct;l||(l=function(e){return e}),c||(c=function(e){return e}),f||(f=function(e,t){for(var n=arguments.length,o=new Array(n>2?n-2:0),r=2;r<n;r++)o[r-2]=arguments[r];return e.apply(t,o)}),m||(m=function(e){for(var t=arguments.length,n=new Array(t>1?t-1:0),o=1;o<t;o++)n[o-1]=arguments[o];return new e(...n)});const p=L(Array.prototype.forEach),d=L(Array.prototype.lastIndexOf),h=L(Array.prototype.pop),g=L(Array.prototype.push),y=L(Array.prototype.splice),T=Array.isArray,b=L(String.prototype.toLowerCase),A=L(String.prototype.toString),S=L(String.prototype.match),E=L(String.prototype.replace),_=L(String.prototype.indexOf),N=L(String.prototype.trim),O=L(Number.prototype.toString),D=L(Boolean.prototype.toString),R="undefined"==typeof BigInt?null:L(BigInt.prototype.toString),w="undefined"==typeof Symbol?null:L(Symbol.prototype.toString),I=L(Object.prototype.hasOwnProperty),v=L(Object.prototype.toString),C=L(RegExp.prototype.test),x=(k=TypeError,function(){for(var e=arguments.length,t=new Array(e),n=0;n<e;n++)t[n]=arguments[n];return m(k,t)});var k;function L(e){return function(t){t instanceof RegExp&&(t.lastIndex=0);for(var n=arguments.length,o=new Array(n>1?n-1:0),r=1;r<n;r++)o[r-1]=arguments[r];return f(e,t,o)}}function M(e,t){let n=arguments.length>2&&void 0!==arguments[2]?arguments[2]:b;if(o&&o(e,null),!T(t))return e;let i=t.length;for(;i--;){let o=t[i];if("string"==typeof o){const e=n(o);e!==o&&(r(t)||(t[i]=e),o=e)}e[o]=!0}return e}function P(e){for(let t=0;t<e.length;t++){I(e,t)||(e[t]=null)}return e}function z(e){const o=s(null);for(const i of n(e)){var r=t(i,2);const n=r[0],a=r[1];I(e,n)&&(T(a)?o[n]=P(a):a&&"object"==typeof a&&a.constructor===Object?o[n]=z(a):o[n]=a)}return o}function U(e,t){for(;null!==e;){const n=a(e,t);if(n){if(n.get)return L(n.get);if("function"==typeof n.value)return L(n.value)}e=i(e)}return function(){return null}}const F=l(["a","abbr","acronym","address","area","article","aside","audio","b","bdi","bdo","big","blink","blockquote","body","br","button","canvas","caption","center","cite","code","col","colgroup","content","data","datalist","dd","decorator","del","details","dfn","dialog","dir","div","dl","dt","element","em","fieldset","figcaption","figure","font","footer","form","h1","h2","h3","h4","h5","h6","head","header","hgroup","hr","html","i","img","input","ins","kbd","label","legend","li","main","map","mark","marquee","menu","menuitem","meter","nav","nobr","ol","optgroup","option","output","p","picture","pre","progress","q","rp","rt","ruby","s","samp","search","section","select","shadow","slot","small","source","spacer","span","strike","strong","style","sub","summary","sup","table","tbody","td","template","textarea","tfoot","th","thead","time","tr","track","tt","u","ul","var","video","wbr"]),H=l(["svg","a","altglyph","altglyphdef","altglyphitem","animatecolor","animatemotion","animatetransform","circle","clippath","defs","desc","ellipse","enterkeyhint","exportparts","filter","font","g","glyph","glyphref","hkern","image","inputmode","line","lineargradient","marker","mask","metadata","mpath","part","path","pattern","polygon","polyline","radialgradient","rect","stop","style","switch","symbol","text","textpath","title","tref","tspan","view","vkern"]),B=l(["feBlend","feColorMatrix","feComponentTransfer","feComposite","feConvolveMatrix","feDiffuseLighting","feDisplacementMap","feDistantLight","feDropShadow","feFlood","feFuncA","feFuncB","feFuncG","feFuncR","feGaussianBlur","feImage","feMerge","feMergeNode","feMorphology","feOffset","fePointLight","feSpecularLine truncated
+//# sourceMappingURL=purify.min.js.map