agent-evaluation-designer

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFE
Full Analysis
  • Instructional Content: The skill serves as a methodology framework for testing AI agents. It does not perform any automated actions, file operations, or network requests.
  • Security Best Practices: The skill explicitly instructs users in Stage 3 to 'Never bake secrets, personal data, or environment-specific paths into cases,' which is a positive security consideration for data handling.
  • Platform Specifics: The references to Microsoft Copilot Studio quotas and limits (e.g., character limits, throttle rates) are informative and align with known platform documentation for development workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:55 PM
Security Audit — agent-trust-hub — agent-evaluation-designer