email-himalaya

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

• Third-party content exposure detected (high risk: 0.90). The skill uses himalaya to read email messages (e.g., the "himalaya message read " and "envelope list" workflows) which ingest and display arbitrary, user-generated emails from configured inboxes—untrusted third‑party content that the agent would read and interpret.