hl-receive-review
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: The skill reads 'review text' or 'review-file paths', which can originate from external contributors via GitHub PR comments or shared files (SKILL.md).
- Capability inventory: The skill is restricted to evaluation and reporting; the instructions explicitly forbid editing code, posting replies, or performing fixes (SKILL.md).
- Boundary markers: No specific delimiters or 'ignore' instructions are used when interpolating the review text into the analysis process.
- Sanitization: No sanitization or filtering of the external input is performed.
Audit Metadata