himalaya-email-manager

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored email content is fetched at runtime from the user’s IMAP account (e.g., via email-summary.py / email-search.py / email_save.py using Himalaya IMAP), and that message body text/headers are then parsed into LLM-readable output (tables/JSON) that the agent can include in its LLM context.