skills/microsoft/waza/waza-runner/Gen Agent Trust Hub

waza-runner

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Configuration-Driven Execution: The skill parses configuration files to execute Python assertions and external scripts. While this constitutes dynamic execution, it is the primary function of the evaluation runner for testing skill performance.
  • Input Processing: The skill ingests data from local task definitions and evaluation specs. Users should ensure these configuration files come from trusted sources as they determine the evaluation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 03:33 PM
Security Audit — agent-trust-hub — waza-runner