Skills
Navigate
skills/testland/qa/llm-regression-suite-author/Gen Agent Trust Hub

llm-regression-suite-author

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices, using GitHub Actions secrets for API key management and avoiding hardcoded credentials.
  • [EXTERNAL_DOWNLOADS]: References official documentation and installation commands for promptfoo and deepeval. These resources originate from established projects and well-known services.
  • [COMMAND_EXECUTION]: Provides instructions for local and CI-based execution of evaluation tools and a utility script. These operations are within the scope of the skill's purpose and do not pose a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 11:03 AM
Security Audit — agent-trust-hub — llm-regression-suite-author