code-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git repositories which could contain adversarial instructions meant to mislead the AI.
- Ingestion points: The agent executes
git diffand reads the full content of changed files as defined in steps 1 and 3 of the instructions. - Boundary markers: The skill lacks explicit delimiters or instructions provided to the agent to distinguish between the code being reviewed and its own instructions, increasing the risk of the agent obeying commands embedded in code comments or strings.
- Capability inventory: The skill utilizes
git status,git diff, and file system read capabilities to perform its analysis. - Sanitization: No sanitization, escaping, or validation of the ingested file content is performed before analysis.
Audit Metadata