himalaya

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill explicitly reads and acts on emails fetched from IMAP/SMTP backends (see SKILL.md commands like "himalaya envelope list" and "himalaya message read" and references/configuration.md IMAP backend configuration), which are untrusted, user-generated third‑party content that can influence replies/forwards/moves.