council
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a sub-agent orchestration pattern to process user input through multiple markdown-defined personas. This is a standard and safe use of agent capabilities.
- [SAFE]: Agent discovery logic correctly limits file access to the skill's own
agents/directory or the standard user agent path~/.claude/Agents/. - [SAFE]: No network exfiltration or sensitive file access patterns were detected. The skill primarily operates on the provided user text.
- [SAFE]: Instructions for spawning sub-agents include a reasonable 5-minute timeout and follow best practices for structured output.
Audit Metadata