email-automation

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and reads user emails from third‑party providers (Gmail/Outlook/IMAP) as described in SKILL.md (e.g., "Read & Summarize Unread Messages", "Search Inbox" and Core Features → Read Email), exposing the agent to untrusted, user-generated content that it is expected to interpret and which can influence subsequent actions.