comfyui-video-generator
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to generate video content, creating a standard surface for indirect prompt injection attacks.
- Ingestion points: 'Scene description', 'Visual style', and 'Reference images' defined in SKILL.md.
- Boundary markers: The instructions lack explicit boundary markers or guidance for the agent to ignore instructions potentially embedded within the user-provided prompts or metadata of reference images.
- Capability inventory: The skill calls an external ComfyUI backend to process these inputs.
- Sanitization: There is no mention of sanitization, filtering, or validation for the 'referenceAssets' or 'prompt' parameters before they are passed to the backend.
- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML configuration without accompanying scripts or executable files.
Audit Metadata