company-people-list

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly ingests and analyzes untrusted third‑party/user‑generated content—e.g., LinkedIn posts and profiles via the Anysite MCP (user_posts/user endpoints), Gmail threads via the Gmail MCP (gmail_search_messages / gmail_read_thread), and meeting notes via the Granola MCP (get_meetings) —and uses those inputs to drive classification, recommendations, and automated actions (Attio notes), so third‑party content can materially influence agent decisions.