waza-interactive

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Standard Command Execution: The skill instructions suggest running waza init <directory> via a terminal to scaffold new evaluation suites. This is a routine development task used for project initialization and does not involve unusual or high-privilege operations.
  • Tool-Based Orchestration: The skill relies on a set of defined MCP tools (e.g., waza_eval_run, waza_skill_check) to perform its primary functions. These tools are scoped to the specific task of evaluating and debugging AI skills, which is consistent with the skill's stated purpose as a workflow partner.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 03:32 PM
Security Audit — agent-trust-hub — waza-interactive