video-sdk/web

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

• Third-party content exposure detected (high risk: 0.75). The runtime workflow ingests outsider-authored free text via Zoom session events—e.g., client.on('chat-on-message', ...) and client.on('command-channel-message', ...) deliver other participants’ message/text strings into the agent’s LLM context if the agent logs/displays them.