himalaya

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

• Third-party content exposure detected (medium risk: 0.30). The Himalaya CLI skill requires the agent to read emails via IMAP/SMTP commands like himalaya message read, directly ingesting untrusted outsider-authored email bodies into the runtime workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions fetch and execute an install script from a GitHub raw URL (https://raw.githubusercontent.com/pimalaya/himalaya/master/install.sh), constituting an unverified runtime external dependency with high provenance risk.