omni-ai-eval
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages model evaluations using the
omniCLI, which is a native tool provided by the vendorexploreomni. - [SAFE]: External references point to the vendor's official documentation at
docs.omni.coand their public GitHub repository atgithub.com/exploreomni/cli. - [SAFE]: Command execution is restricted to the Omni CLI suite for prompt set management and evaluation runs, following standard developer workflows.
- [SAFE]: No signs of obfuscation, credential exfiltration, or persistence mechanisms were found; authentication is handled via the user's local CLI configuration.
Audit Metadata