safe-browser

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches required libraries from the official NPM registry and downloads the Chromium browser using the Playwright utility.
  • [COMMAND_EXECUTION]: Executes shell commands to copy templates, install dependencies, and run the demonstration script.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from external web pages, which constitutes an indirect prompt injection surface.
  • Ingestion points: The extractFrontPage and extractComments functions in hn-scraper-demo.mjs use Playwright's page.$$eval to read data from the browser's Document Object Model.
  • Boundary markers: The generated agent's system prompt explicitly instructs it to treat page content as untrusted and restricts its operations to the safe_browser tool.
  • Capability inventory: The runtime environment maintains file-writing capabilities for generating artifacts and network access through a controlled browser instance.
  • Sanitization: The safe_browser tool enforces a strict domain allowlist (news.ycombinator.com) using CDP Fetch.requestPaused interception and only exposes high-level extraction actions rather than raw browser control.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:47 AM
Security Audit — agent-trust-hub — safe-browser