deepline-plays-review

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads Google Sheets values and Drive comments via Google Workspace API requests, which can contain outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.70). The instruction references https://code.deepline.com/api/v2/npm/ and https://code.deepline.com/INSTALL.md as setup and installation sources for the Deepline package and CLI, constituting an unverified external operational dependency under weak/unknown provenance.