p-video

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly shows supplying external image/audio URLs (e.g., the "Image-to-Video" and "With Audio" examples using "https://your-image.jpg" and "https://your-audio.mp3") which the CLI/app will fetch and ingest as untrusted third‑party content that can directly influence model outputs and behavior.