skills/oldwinter/skills/browser/Gen Agent Trust Hub

browser

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/start.cjs script uses child_process.spawn to launch the Chrome browser process based on the operating system.
  • Evidence: const chrome = spawn(chromePath, args, { detached: true, stdio: 'ignore' }); in scripts/start.cjs.
  • [INDIRECT_PROMPT_INJECTION]: The skill navigates to external websites and processes their content (DOM elements, text, evaluation results), creating a surface for instructions embedded in web pages to influence agent behavior.
  • Ingestion points: nav.cjs (navigation to external URLs), eval.cjs (executing JS on pages), and pick.cjs (inspecting DOM elements).
  • Boundary markers: None identified; the agent is not explicitly instructed to ignore or sanitize content found on processed web pages.
  • Capability inventory: The agent can execute arbitrary JavaScript in the browser (eval.cjs), navigate to new URLs (nav.cjs), and save screenshots to the local file system (screenshot.cjs).
  • Sanitization: No sanitization or filtering of retrieved web content is performed before returning it to the agent context.
  • [DYNAMIC_EXECUTION]: The scripts/eval.cjs script accepts arbitrary JavaScript code as a command-line argument and executes it within the browser context using the Runtime.evaluate method of the Chrome DevTools Protocol.
  • Evidence: ws.send(JSON.stringify({ id: 1, method: 'Runtime.evaluate', params: { expression: code, ... } })); in scripts/eval.cjs.
  • [DATA_EXPOSURE]: The skill manages sensitive browser data and screenshots locally.
  • Persistent Profiles: scripts/start.cjs supports a --profile flag that stores cookies, authentication tokens, and browser history in ~/.chrome-debug-profile, which could be accessed by subsequent browser sessions.
  • Temporary Files: scripts/screenshot.cjs writes browser screenshots to the system's temporary directory using os.tmpdir().
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 01:53 PM