gstack/browse
Garry Tan 808ce0de8e
fix(security): wrap snapshot output in untrusted-content envelope
The sidebar system prompt pushes the agent to run \`\$B snapshot\` as its
primary read path, but snapshot was NOT in PAGE_CONTENT_COMMANDS, so its
ARIA-name output flowed to Claude unwrapped. A malicious page's
aria-label attributes became direct agent input without the trust
boundary markers that every other read path gets.

Adding 'snapshot' to the set runs the output through
wrapUntrustedContent() like text/html/links/forms already do.

Caught by codex adversarial review.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 11:06:45 +08:00
..
bin feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00
scripts fix: ngrok Windows build + close CI error-swallowing gap (v0.18.0.1) (#1024) 2026-04-16 13:49:04 -07:00
src fix(security): wrap snapshot output in untrusted-content envelope 2026-04-20 11:06:45 +08:00
test test(security): source-level contracts for the security wiring 2026-04-20 07:09:52 +08:00
PLAN-snapshot-dropdown-interactive.md fix: snapshot -i auto-detects dropdown/popover interactive elements (#845) 2026-04-05 22:57:45 -07:00
SKILL.md fix(preamble): emit EXPLAIN_LEVEL + QUESTION_TUNING bash echoes 2026-04-20 07:05:43 +08:00
SKILL.md.tmpl feat(browse): Puppeteer parity — load-html, screenshot --selector, viewport --scale, file:// (v1.1.0.0) (#1062) 2026-04-18 23:25:33 +08:00