codewiki
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The Python wrapper
codewiki.pyutilizessubprocess.runto call the local Node.js scraper tool. This is a common pattern for integrating tools across different runtime environments. - [EXTERNAL_DOWNLOADS]: The documentation points to the author's GitHub repository (
github.com/zurybr/codewiki-cli) for installation, and the tool performs automated browsing of thecodewiki.googledomain to extract documentation data. - [PROMPT_INJECTION]: The skill scrapes and outputs external content from the web, which creates a potential surface for indirect prompt injection if the source content contains adversarial instructions.
- Ingestion points:
codewiki.jsextracts content fromhttps://codewiki.google/using Puppeteer'spage.evaluate(). - Boundary markers: The scraped data is printed to standard output without specific delimiters or warnings to differentiate external content from agent instructions.
- Capability inventory: The skill possesses the ability to launch a browser (
puppeteer) and execute subprocesses (subprocess.run). - Sanitization: No sanitization or filtering is applied to the extracted
innerTextbefore it is displayed to the user or agent.
Audit Metadata