alicloud-ai-video-wan-r2v

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md and scripts/prepare_r2v_request.py explicitly accept a reference_video (demonstrated as a public URL like https://example.com/reference.mp4) that the Wan R2V model ingests to guide generation, so arbitrary third‑party content could materially influence the agent's outputs.