code-review-gate
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is local code analysis. It uses git commands and direct file access to read source code and perform pattern matching. All operations are transparent and consistent with the stated purpose of a code review tool. No external downloads or sensitive data exfiltration patterns were detected.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and processes untrusted source code from a repository. This is an inherent risk of code review tools. 1. Ingestion points: Source code files identified via git diff or user selection. 2. Boundary markers: No explicit delimiters or instructions are used to separate the code being scanned from the agent's instructions. 3. Capability inventory: The skill can read files, write auto-fixes to the local file system, and generate text reports. 4. Sanitization: The content is processed using regular expressions for pattern matching; there is no specific sanitization of embedded natural language instructions within the code files.
Audit Metadata