alicloud-ai-video-animate-anyone

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill requires the agent to ingest arbitrary public HTTP/HTTPS input files (see "Prerequisites: Input files must be public HTTP/HTTPS URLs" in SKILL.md and the --image-url/--video-url arguments in scripts/prepare_animate_anyone_request.py), so untrusted third‑party images/videos are read and used to drive detection/template generation and downstream actions.