Fix HTML export URL sanitization

packages/coding-agent/CHANGELOG.md

@@ -10,6 +10,7 @@
 
 ### Fixed
 
+- Fixed stored XSS in HTML session exports by sanitizing Markdown link and image URLs with a scheme allow-list after stripping control characters.
 - Fixed SDK embedding in bundled Node apps failing with `ENOENT` when `package.json` is not present next to the bundle entrypoint. The package metadata reader now gracefully handles missing `package.json` by using defaults, enabling `createAgentSession()` without requiring package-adjacent files at runtime ([#5226](https://github.com/earendil-works/pi/issues/5226)).
 - Fixed HTTP timeout setting not being respected for non-Codex providers (e.g., llama.cpp via OpenAI-compatible API). The `httpIdleTimeoutMs` setting (set via `/settings` HTTP timeout) now applies as the default SDK request timeout for all providers that support it, not just OpenAI Codex Responses. Disabling the timeout (HTTP timeout = false) now correctly disables SDK timeouts for all supported providers by sending a maximum int32 value (effectively infinite) instead of 0, since SDKs treat timeout=0 as an immediate timeout ([#5294](https://github.com/earendil-works/pi/issues/5294)).
 - Fixed opening and listing very large JSONL session files by reading session entries line-by-line instead of materializing the full file as one string ([#5231](https://github.com/earendil-works/pi/issues/5231)).

packages/coding-agent/src/core/export-html/template.js

@@ -613,6 +613,18 @@
           .replace(/'/g, ''');
       }
 
+      function sanitizeMarkdownUrl(value) {
+        const href = String(value || '').trim().replace(/[\x00-\x1f\x7f]/g, '');
+        if (!href) return href;
+
+        const scheme = href.match(/^([A-Za-z][A-Za-z0-9+.-]*):/);
+        if (scheme && !/^(https?|mailto|tel|ftp)$/i.test(scheme[1])) {
+          return null;
+        }
+
+        return href;
+      }
+
       /**
        * Truncate string to maxLen chars, append "..." if truncated.
        */
@@ -1569,10 +1581,11 @@
           }
         },
         renderer: {
-          // Sanitize link URLs to prevent javascript:/vbscript:/data: XSS
+          // Sanitize link URLs with a scheme allow-list. Browsers strip C0
+          // controls from schemes, so strip them before checking and emitting.
           link(token) {
-            const href = (token.href || '').trim();
-            if (/^\s*(javascript|vbscript|data):/i.test(href)) {
+            const href = sanitizeMarkdownUrl(token.href);
+            if (href === null) {
               return this.parser.parseInline(token.tokens);
             }
             let out = '<a href="' + escapeHtml(href) + '"';
@@ -1582,10 +1595,10 @@
             out += '>' + this.parser.parseInline(token.tokens) + '</a>';
             return out;
           },
-          // Sanitize image src URLs
+          // Sanitize image src URLs with the same scheme allow-list.
           image(token) {
-            const href = (token.href || '').trim();
-            if (/^\s*(javascript|vbscript|data):/i.test(href)) {
+            const href = sanitizeMarkdownUrl(token.href);
+            if (href === null) {
               return escapeHtml(token.text || '');
             }
             let out = '<img src="' + escapeHtml(href) + '" alt="' + escapeHtml(token.text || '') + '"';

packages/coding-agent/test/export-html-xss.test.ts

@@ -4,15 +4,20 @@ import { describe, expect, it } from "vitest";
 describe("export HTML markdown link sanitization", () => {
 	const templateJs = readFileSync(new URL("../src/core/export-html/template.js", import.meta.url), "utf-8");
 
-	it("overrides the marked link renderer to block javascript: protocol", () => {
-		// The custom link renderer must check for dangerous protocols
+	it("overrides the marked link renderer to use scheme allow-list sanitization", () => {
 		expect(templateJs).toMatch(/link\s*\(\s*token\s*\)/);
-		expect(templateJs).toMatch(/javascript/i);
-		expect(templateJs).toMatch(/vbscript/i);
+		expect(templateJs).toMatch(/sanitizeMarkdownUrl\(token\.href\)/);
+		expect(templateJs).toMatch(/\^\(https\?\|mailto\|tel\|ftp\)/);
 	});
 
-	it("overrides the marked image renderer to block javascript: protocol", () => {
+	it("overrides the marked image renderer to use scheme allow-list sanitization", () => {
 		expect(templateJs).toMatch(/image\s*\(\s*token\s*\)/);
+		expect(templateJs).toMatch(/sanitizeMarkdownUrl\(token\.href\)/);
+	});
+
+	it("strips C0 controls before checking and emitting markdown URLs", () => {
+		expect(templateJs).toContain("replace(/[\\x00-\\x1f\\x7f]/g, '')");
+		expect(templateJs).not.toMatch(/\^\\s\*\(javascript\|vbscript\|data\):/i);
 	});
 
 	it("escapes href attributes in the custom link renderer", () => {