mental-model-mapper
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized network behaviors were identified. The skill's primary function is to provide a structured prompt for qualitative analysis.
- [NO_CODE]: The skill consists exclusively of instructional documentation and a prompt template; it does not include or execute any external scripts or binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for user-provided data via the system_focus, context, and visible_evidence variables in SKILL.md. While it lacks explicit input sanitization or boundary markers, the absence of any high-privilege capabilities or tool access prevents this surface from being exploited for harmful actions.
Audit Metadata