zoom-rtms

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly ingests untrusted user-generated content (meeting transcripts and chat) delivered via RTMS webhooks and media WebSocket streams (see SKILL.md, examples/manual-websocket.md handling msg_type 17/18 and examples/ai-integration.md where transcripts/chats are fed to AI summarizers), and that content is used to make decisions and drive actions (summaries, sentiment analysis, stream subscription), so third-party content could indirectly inject instructions.