agent-eval
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as documentation for the 'agent-eval' tool and provides clear instructions for its use.
- [COMMAND_EXECUTION]: The skill describes a tool that executes user-defined commands (e.g., pytest, npm run build) for judging agent performance. This is the intended functionality of the benchmarking tool and is documented transparently.
- [EXTERNAL_DOWNLOADS]: The skill provides a link to an external GitHub repository (github.com/joaquinhuigomez/agent-eval) for the tool's source code. It appropriately recommends that users review the source code before installation, adhering to security best practices.
Audit Metadata