council
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate multi-agent orchestration pattern for decision facilitation. It uses the platform's native agent dispatching tools to coordinate between domain archetypes stored in the project structure.
- [PROMPT_INJECTION]: The skill ingests user-provided dilemmas and constraints in SKILL.md, creating a surface for indirect prompt injection where a user could attempt to influence sub-agent behavior. This is mitigated by the facilitator's instructions to validate and re-dispatch sub-agent responses and the overall lack of dangerous system or network tools available to the skill. Ingestion points: user dilemma and constraints; Boundary markers: absent; Capability inventory: agent tool calls and markdown text generation; Sanitization: none.
- [SAFE]: No evidence of hardcoded credentials, malicious network requests, or unauthorized file system operations was found.
Audit Metadata