himalaya
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). Himalaya explicitly fetches and reads emails from IMAP backends (see SKILL.md "himalaya message read", "envelope list" and references/configuration.md IMAP backend.host settings), which are untrusted, user-generated third‑party messages that the agent is expected to interpret and can directly trigger actions like reply/forward/move/delete, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata