cekura-predefined-metrics
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation and implementation guide for Cekura's built-in evaluation metrics. It does not contain executable code or scripts.
- [SAFE]: All network endpoints described (e.g.,
test_framework/v1/predefined-metrics/) and domains (e.g.,cekura.ai) are part of the official vendor infrastructure associated with the skill's stated purpose. - [SAFE]: The handling of sensitive data (API keys) follows security best practices by using placeholders like
<key>and{project_id}in documentation examples. - [SAFE]: No patterns of prompt injection, obfuscation, or unauthorized data exfiltration were detected. The skill's behavior strictly aligns with its manifest and description.
Audit Metadata