repo-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external repository code changes, which presents a surface where malicious instructions hidden in code comments or metadata could attempt to influence the agent's behavior.
- Ingestion points: External code files and repository diffs processed during the review.
- Boundary markers: The instructions do not define specific delimiters to separate untrusted code from agent instructions.
- Capability inventory: No scripts or additional tools are provided; execution is limited to standard file reading and text generation.
- Sanitization: No specific sanitization or filtering steps are defined for the input data.
- [NO_CODE]: The skill contains only documentation and instructional text in the SKILL.md file and does not include any executable scripts or binary files.
Audit Metadata