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