@1247/web-crawler
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing untrusted data from the web.\n
- Ingestion points: Untrusted data is retrieved from arbitrary URLs in
scripts/crawl.pyvia Playwright.\n - Boundary markers: The skill lacks delimiters or explicit warnings to the agent that the output data (text and audit reports) is untrusted.\n
- Capability inventory: The skill can write files to the local output directory and execute browser interactions.\n
- Sanitization: No escaping or validation is performed on the extracted text or console logs before they are saved.\n- [EXTERNAL_DOWNLOADS]: The skill downloads the Playwright framework and the Chromium browser engine as part of its setup process.\n- [COMMAND_EXECUTION]: The skill executes shell commands to install browser binaries and system-level dependencies during installation.
Audit Metadata