eval-best-practices

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The evals/run-static-checks.sh script executes shell commands to determine the repository layout and run a Python-based static checker (check-skill-static.py). This script is a development utility and operates within the local repository environment.
  • [SAFE]: The skill provides structured guidance on evaluation contracts, task fidelity, and judge calibration. All reference materials and evaluation datasets are provided in plain text and standard JSON formats without obfuscation or suspicious external dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 05:27 PM
Security Audit — agent-trust-hub — eval-best-practices