general-vs-special
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary purpose is to provide an instructional framework for the AI agent to perform code reviews. The instructions are purely pedagogical and do not contain any attempt to bypass safety filters or exfiltrate data.
- [COMMAND_EXECUTION]: The skill uses the 'Read' and 'Grep' tools to analyze code provided in the arguments. These are standard, low-risk operations within the scope of a code analysis task.
- [DATA_EXPOSURE]: No sensitive file paths, hardcoded credentials, or network operations were detected. The data access is restricted to the files explicitly provided by the user for review.
- [PROMPT_INJECTION]: While the skill processes external data (code files) that could theoretically contain indirect prompt injections, the risk is mitigated because the skill does not have access to sensitive tools, shell execution, or network capabilities. No explicit boundary markers are present, but the scope of actions remains limited to analysis.
Audit Metadata