lipsync

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-supplied open/public media URLs (see the Invoke examples with "video_url"/"audio_url"/"image_url" and the "How it works" / "Indirect prompt injection (third-party content)" sections) so untrusted audio/video/image content can be read and materially influence model generation and subsequent tool actions.