meeting-briefing

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests “Recent correspondence,” “Messages,” and “Meeting agendas and prior meeting notes” from connected sources like Email/Chat/Documents, which can include outsider-authored free-form text (e.g., messages/comments from participants other than the operating user) that the agent then synthesizes into the LLM briefing context.