agency-email-intelligence-engineer

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a pipeline that reads and parses raw email content via IMAP/Gmail/Microsoft Graph (e.g., fetch_thread reads RFC822 message bytes and extract_body); if an outsider can cause their free-text email content to enter the mailbox/queue the workflow processes, that free text is ingested and assembled into LLM-ready context.