six-thinking-hats
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and YAML metadata for guiding LLM reasoning.\n- [NO_CODE]: There are no scripts, binaries, or command-line executions defined within the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided focus questions. 1. Ingestion points: Focus questions and emotions in SKILL.md. 2. Boundary markers: Mandatory hat-labeled sections and specific bullet labels ([KNOWN], [ASSUMED]) act as delimiters. 3. Capability inventory: No tools, network access, or file-system permissions. 4. Sanitization: None, as the output is purely textual.
Audit Metadata