code-review
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as code diffs, patches, and pull request information, which may contain malicious instructions.
- Ingestion points: Untrusted data enters the agent's context through the review of change sets, patches, and issue descriptions as outlined in SKILL.md.
- Boundary markers: Absent; there are no instructions to use specific delimiters or to ignore potential commands embedded in the code being reviewed.
- Capability inventory: The skill workflow in SKILL.md recommends running repository checks and quality gates, which implies the execution of build tools or test scripts on the analyzed code.
- Sanitization: Absent; the skill does not define methods for filtering or escaping instructions that might be present in code comments or metadata.
Audit Metadata