puppeteer-skill

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Puppeteer to spawn and manage browser processes. Standard automation configurations are provided, including flags for environment compatibility such as --no-sandbox and --disable-setuid-sandbox.
  • [PROMPT_INJECTION]: The skill provides patterns for extracting content from web pages via page.$eval and page.evaluate, which creates a surface for indirect prompt injection.
  • Ingestion points: Scraping logic in SKILL.md and reference/playbook.md.
  • Boundary markers: None present in the code patterns.
  • Capability inventory: Subprocess management (browser), file writing (screenshots/PDFs), and network access (navigation).
  • Sanitization: Not included in the provided implementation examples.
  • [EXTERNAL_DOWNLOADS]: Facilitates connection to TestMu AI's cloud infrastructure via wss://cdp.lambdatest.com. This allows for remote browser execution through the vendor's official services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 11:51 PM