mental-models
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
00-system/mental-models/scripts/select_mental_models.pyto manage and filter the internal library of mental models. This is used for indexing and listing available resources. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for user-provided problem contexts which are used to suggest relevant thinking frameworks.
- Ingestion points: User-provided descriptions of problems, decisions, or plans are processed to select appropriate models.
- Boundary markers: Absent; the skill relies on the agent to interpret the user's intent to select a framework.
- Capability inventory: Includes execution of a local Python script and reading of local markdown files.
- Sanitization: Absent; however, the risk is negligible as the skill only loads static, developer-provided framework templates from its own directory structure.
Audit Metadata