ai-video-generation

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

• Third-party content exposure detected (high risk: 0.80). The skill's CLI examples and workflow explicitly accept and fetch arbitrary external URLs for images, audio, and video (e.g., "image_url", "audio_url", "video_url" in SKILL.md examples like belt app run falai/wan-2-5 --input '{"image_url":"https://your-image.jpg"}'), which means untrusted third-party content is ingested and can influence generation behavior.