venice

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly lets the agent trigger Venice to fetch and scrape arbitrary web pages (via venice_parameters like enable_web_search and enable_web_scraping documented in SKILL.md and implemented in exports.chat_with_venice_parameters), and also accepts user-provided http(s) URLs/YouTube links for image_edit, video_queue/video_generate (image_url, video_url, audio_url, reference_image_urls) and video_transcribe_youtube — all of which ingest untrusted public/user-generated content that can influence completions and subsequent actions.