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