minimax-h3-video

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading model files and workflow configurations from external repositories.\n
  • Evidence: Model weights are sourced from huggingface.co/Comfy-Org/MiniMax-H3.\n
  • Evidence: Workflow templates are fetched from github.com/Comfy-Org/workflow_templates.\n
  • Evidence: Community-developed LoRAs are referenced from lightx2v/Minimax-h3-Turbo and Kijai/MiniMax-H3_comfy.\n
  • Evidence: The skill mentions installing a vendor skill via npx skills add from github.com/MiniMax-AI/MiniMax-H3.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that processes user-supplied text for video generation, which is a potential surface for indirect prompt injection.\n
  • Ingestion points: The prompt widget of the MiniMaxH3ImageToVideo node in the SKILL.md node graph description.\n
  • Boundary markers: Absent; there are no instructions to delimit user input or prevent the model from following embedded instructions.\n
  • Capability inventory: The skill leverages capabilities for model downloading (download_model), workflow execution (panel_load_workflow), and file system interaction (save_workflow, upload_image).\n
  • Sanitization: No sanitization logic for input prompts is specified in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 01:59 PM
Security Audit — agent-trust-hub — minimax-h3-video