wan-t2v-video
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill outlines workflows that process user-supplied text prompts to generate videos and save them to disk, which is a standard surface for indirect prompt injection.
- Ingestion points: CLIPTextEncode nodes in the provided JSON workflow templates receive text prompts.
- Boundary markers: The instructions do not specify any delimiters to isolate untrusted input.
- Capability inventory: The system includes the VHS_VideoCombine node for writing files to the local environment.
- Sanitization: The documentation does not include input filtering or sanitization steps.
Audit Metadata