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 examples and workflow show passing arbitrary external URLs (e.g., "image_url", "video_url", "audio_url" with values like "https://your-image.jpg" / "https://your-video.mp4") to inference.sh apps, which fetch and ingest untrusted public media that can influence model outputs and downstream actions.