skills/acedatacloud/skills/wan-video/Gen Agent Trust Hub

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-wan Python 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, and audio_url parameters in requests to the /wan/videos endpoint.\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are described in the provided workflows.\n
  • Capability inventory: The skill uses curl to perform network operations, sending data to the api.acedata.cloud domain.\n
  • Sanitization: The documentation does not specify any sanitization, filtering, or validation logic for the user-provided inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 03:28 AM
Security Audit — agent-trust-hub — wan-video