code-review
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external source code, which constitutes an untrusted data ingestion surface.
- Ingestion points: Processes source code files, pull request diffs, and developer comments during the code review task.
- Boundary markers: The instructions do not specify explicit boundary markers (e.g., XML tags or delimiters) to separate the code being reviewed from the agent's operational instructions.
- Capability inventory: The skill is limited to providing analysis and generating feedback reports; it does not define file-write, network, or subprocess capabilities, though it relies on the host agent's existing toolset.
- Sanitization: No specific sanitization or escaping logic is prescribed for handling untrusted code content before interpolation into the agent's context.
Audit Metadata