himalaya
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes email from external IMAP/SMTP backends (see SKILL.md commands like "himalaya message read 42" and references/configuration.md), ingesting untrusted, user-generated messages which the agent can read and then reply/forward/move/delete, so third-party content can materially influence actions.
Audit Metadata