consciousness-council
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks detected. The skill defines a structured role-playing deliberation process for decision-making.
- [SAFE]: The skill processes untrusted user input (questions/dilemmas) which represents a surface for indirect prompt injection; however, it lacks instructions that would exploit this surface or facilitate an attack. Evidence:
- Ingestion points: User-provided questions for council deliberation in SKILL.md.
- Boundary markers: None present to delimit user input from instructions.
- Capability inventory: Access to 'Read' and 'Write' tools as defined in YAML frontmatter.
- Sanitization: No explicit sanitization or validation of user-provided content is performed.
- [SAFE]: External references point to documentation and official sites associated with the author's stated organization (AHK Strategies), which is consistent with legitimate skill development.
Audit Metadata