openrouter-benchmarks
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and designed to help an agent query the official OpenRouter Benchmarks API at openrouter.ai. All documented network operations target the vendor's own domain.
- [SAFE]: No evidence of credential exfiltration, malicious command execution, or persistence mechanisms was found. The instructions for using the OPENROUTER_API_KEY follow standard environment variable practices.
- [SAFE]: The skill includes safety-conscious logic, such as the 'Availability Gate' section, which instructs the agent to verify model availability before making recommendations, preventing the agent from providing dated or non-actionable information.
Audit Metadata