google-drive

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

• Third-party content exposure detected (low risk: 0.10). The Google Drive skill searches and lists files from the user's Google Drive storage account, where outsider-authored content can be present in shared files or document titles, yielding a low indirect prompt injection risk via explicit search or fetch actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill utilizes an unverified third-party cloud function domain for OAuth authentication and token refreshing, presenting a weak operational dependency.