zoom-mcp

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

• Third-party content exposure detected (high risk: 0.70). The skill calls Zoom MCP endpoints (e.g., search_meetings, get_meeting_assets, get_recording_resource against https://mcp.zoom.us) and the workflows in SKILL.md and examples/transcript-retrieval.md show the agent is expected to read meeting recaps/transcripts and linked assets (user-generated third-party content) which can materially influence subsequent tool calls and actions.