code-review
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted data from source code files, directories, and pull requests.
- Ingestion points: Content from files, directories, and pull requests passed via arguments such as
[file],[directory], or[pr](SKILL.md). - Boundary markers: The instructions do not define clear boundaries or 'ignore' directives to help the agent distinguish between code-under-review and operational instructions.
- Capability inventory: The skill is granted access to high-privilege tools including
Bash,Task, andLSP(SKILL.md), which increases the potential impact of a successful injection. - Sanitization: No sanitization or validation logic is defined for the content of the files being processed.
Audit Metadata