consciousness-council
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to drive its multi-archetype deliberation process, creating a surface for indirect prompt injection attacks.
- Ingestion points: User-provided questions, decisions, and challenges described in Phase 1 of SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or provide warnings to ignore instructions embedded within the user data.
- Capability inventory: The skill permits use of the Read and Write tools through its YAML frontmatter configuration.
- Sanitization: No sanitization, validation, or filtering mechanisms are present to check the integrity of input data before it is processed by the archetypes.
Audit Metadata