gmail

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests email messages from an outsider-accessible inbox via Gmail fetch/reply actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of external third-party CLI packages via npx without an explicit verifiable publisher provenance or integrity guarantee, representing an unverified runtime dependency.