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
Risk Level
SAFE
Analyzed
May 14, 2026, 04:15 PM