address-pr-review
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Pull Request review comments, which are untrusted external data sources.
- Ingestion points: Data enters the agent's context through the instruction to "Review the PR comments" (SKILL.md).
- Boundary markers: The instructions lack delimiters or explicit "ignore embedded instructions" warnings for the external data.
- Capability inventory: The skill description states "This skill changes code," indicating the agent has file-system modification capabilities while acting on the untrusted input.
- Sanitization: No input validation, filtering, or sanitization steps are defined to prevent malicious comments from being executed as instructions.
Audit Metadata