videodb

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the capture/RTStream WebSocket event pipeline: scripts/ws_listener.py ingests msg["data"]["text"] from real-time transcription/visual indexing (originating from other people’s speech/screen content) and writes it to videodb_events.jsonl, which the skill’s workflows then use as transcript/scene text for LLM operations like coll.generate_text(prompt=...).