himalaya

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly reads and acts on user-generated third-party email content from configured IMAP servers (see SKILL.md commands like "himalaya message read 42" and references/configuration.md IMAP backend), meaning untrusted email body/attachments can be ingested and influence replies, forwards, downloads, or other actions.