mayor-coordinator
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill maintains rigorous separation between coordination and execution, operating exclusively through a local state management API.
- [PROMPT_INJECTION]: The skill processes inter-agent communications, which presents an indirect prompt injection surface. [Ingestion points]: The skill reads JSON messages from '.chipset/state/mail/' (SKILL.md). [Boundary markers]: No explicit isolation or 'ignore' instructions for message payloads were observed. [Capability inventory]: The skill can spawn or terminate agents and assign work via hooks (SKILL.md). [Sanitization]: The documentation does not specify sanitization or validation of message contents.
Audit Metadata