wan-video
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill accepts and processes arbitrary user-provided images/videos via refly file upload and the input_image/input_video file IDs (and downloads files from refly workflow/toolcalls) so the agent ingests untrusted, user-generated third-party content as part of image-to-video and video-to-video processing.
Audit Metadata