comfyui

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill handles community-provided workflows through workflow_json and workflow_path parameters. This is an inherent ingestion surface for the skill's primary purpose. Evidence: SKILL.md describes converting community workflows into tool calls.
  • [EXTERNAL_DOWNLOADS]: The skill mentions downloading models and custom nodes using standard community tools like ComfyUI Manager. Evidence: instructions in SKILL.md under 'Model and LoRA Setup' and 'Failure Handling'.
  • [COMMAND_EXECUTION]: The skill defines parameters for executing specialized image, video, and music generation tools but does not contain patterns for arbitrary shell command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:31 PM