connect-google

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads emails, calendar events, and drive/docs contents via the gog CLI tool, which ingests untrusted user content (such as email bodies and document texts) during typical agent operations.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill downloads an external script (gog-oauth.sh) from an arbitrary GitHub repository (Melvynx/ai-maxxing-skills), constituting an unverified third-party runtime dependency.