meeting-prep

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

• Third-party content exposure detected (high risk: 0.78). Outsider free text can enter the LLM context via runtime ingestion of external meeting attendee data from person-lookup (e.g., LinkedIn profiles/recent posts) and external company/news content from company-intel (e.g., web-fetched intelligence), which are authored by third parties not chosen by the operating user.