claude-review
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for invoking the mcp__claude-code__claude_code MCP tool. It correctly implements a permissionMode: plan parameter, ensuring the delegated review session is read-only and cannot modify the filesystem.
- [SAFE]: The configuration in agents/openai.yaml disables implicit invocation (allow_implicit_invocation: false). This is a security best practice that prevents the agent from triggering the skill automatically, avoiding potential infinite loops.
- [SAFE]: While the skill processes external code files (an indirect prompt injection surface), it operates in a restricted planning mode that prevents unauthorized file modifications, maintaining a safe execution environment.
Audit Metadata