consciousness-council
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process user-provided challenges and dilemmas, which naturally exposes it to potential indirect prompt injection if a user includes malicious instructions in their query.\n
- Ingestion points: The user question, decision, or creative challenge described in SKILL.md (Phase 1).\n
- Boundary markers: No explicit boundary markers or delimiters are defined to wrap the user input within the prompts.\n
- Capability inventory: The skill allows access to Read and Write tools, though the instructions primarily focus on text generation.\n
- Sanitization: There are no instructions for sanitizing user-provided content before it is processed by the archetypes.\n- [SAFE]: The skill does not exhibit any patterns of obfuscation, exfiltration, or unauthorized privilege escalation. All external links are for documentation and attribution to the developer's official sites.
Audit Metadata