agency-email-intelligence-engineer

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow ingests and parses raw email bodies from the operating user’s email source (e.g., IMAP/Gmail/Graph) and then assembles that readable text into the agent context; this is outsider-authored free text because the email content is written by other correspondents, not the operating user.