wan-video
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill mentions the installation of the
mcp-wanPython package, which is a resource provided by the author to facilitate use of the video generation service.\n- [PROMPT_INJECTION]: The skill processes user-supplied text prompts and external media URLs, establishing an interface for potential indirect prompt injection through external data sources.\n - Ingestion points: Data enters the system via the
prompt,image_url,reference_video_urls, andaudio_urlparameters in requests to the/wan/videosendpoint.\n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are described in the provided workflows.\n
- Capability inventory: The skill uses
curlto perform network operations, sending data to theapi.acedata.clouddomain.\n - Sanitization: The documentation does not specify any sanitization, filtering, or validation logic for the user-provided inputs.
Audit Metadata