minimax-h3
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text prompts and external media references to generate video clips. This presents a surface for potential instruction injection via user-controlled inputs.\n
- Ingestion points: User prompts and reference media passed to video generation tools.\n
- Boundary markers: None identified in the skill instructions.\n
- Capability inventory: Tool calls to external video generation APIs and local ComfyUI workflow execution.\n
- Sanitization: No explicit input sanitization or validation is described for the prompt or media content.\n- [DYNAMIC_EXECUTION]: The skill facilitates the use of local ComfyUI by accepting JSON-based workflows. This involves dynamic execution within the specialized ComfyUI environment to process video generation graphs.
Audit Metadata