consciousness-council
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied questions and dilemmas through various 'archetypes'. This creates a standard surface where untrusted user input is interpreted by the agent.
- Ingestion points: User-provided "question, decision, or creative challenge" as described in the deliberation phases.
- Boundary markers: None explicitly defined in the deliberation templates to encapsulate user input.
- Capability inventory: The skill has access to
ReadandWritetools. - Sanitization: No specific sanitization or escaping of user input is described.
- [SAFE]: The skill implements 'Integrity rules' that explicitly instruct the agent to avoid fabricating results or citations, label speculation clearly, and verify information against official documentation.
- [SAFE]: The operating procedure includes a mandatory check to ask for user consent before performing actions that incur costs, consume cloud quotas, or access personal or patient data.
Audit Metadata