NYC

himalaya

Warn

Audited by Snyk on Feb 16, 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 connects to user-configured IMAP/SMTP servers (see config.toml backend.host/login) and directly reads and displays message bodies, MIME parts, and attachments via commands like "himalaya message read", "envelope list", and "attachment download", which are untrusted, user-generated third-party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:02 AM