review-code
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code from the local working tree and is authorized to execute file modifications based on that input.\n
- Ingestion points: All changed files in the working tree (staged and unstaged) as specified in the Scope section of
SKILL.md.\n - Boundary markers: The prompt lacks explicit delimiters or instructions to treat embedded text in analyzed files as data rather than instructions, which could allow maliciously crafted code comments to influence agent behavior.\n
- Capability inventory: The skill instructions allow the agent to 'apply it directly with Edit', a high-privilege capability that could be abused if the agent is successfully injected.\n
- Sanitization: No sanitization or filtering logic is present to identify or ignore potentially malicious patterns within the source code being reviewed.
Audit Metadata