videodb

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and processes arbitrary public/user-generated content (e.g., coll.upload(url="https://..."), YouTube uploads, coll.connect_rtstream(url=...), RTSP/RTMP sources) and then runs AI indexing/search/visual-audio LLM pipelines (see SKILL.md, reference/rtstream-reference.md and capture-reference.md) whose outputs (websocket events, scene/index results, alerts, transcripts) the agent is expected to read and act on (search, compile streams, create alerts), so untrusted third‑party content can materially influence tool use and actions.