ai-video-generation

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests user-provided third‑party assets (e.g., "audio_url" in the Wan 2-7 examples and "image_url" in multiple i2v invokes) and the SKILL.md Security & Privacy section acknowledges those external URLs are untrusted and can influence generation, so untrusted content is fetched/used and can materially affect tool behavior.