venice-video

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents a /video/transcriptions endpoint that takes a YouTube URL (and the QueueVideoRequest accepts arbitrary image_url/video_url/audio_url/reference_image_urls) so the agent will ingest transcripts or media from untrusted public sources and could act on their content, enabling indirect prompt injection.