ah-verify-requirements-coverage
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources.\n
- Ingestion points: Fetches issue descriptions and PR bodies using
gh issue view(Step 5) andgh pr view(Step 3).\n - Boundary markers: The procedure does not specify the use of delimiters or 'ignore' instructions when passing the external content to the LLM for analysis in Step 8.\n
- Capability inventory: No high-risk capabilities (like file-writing, network POSTs to non-whitelisted domains, or
evalusage) were detected; the skill primarily generates a text report.\n - Sanitization: The skill does not perform sanitization or filtering on the retrieved GitHub content before processing.
Audit Metadata