google-drive-automation

Warn

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the user to execute local Python scripts (scripts/auth.py and scripts/drive.py) to manage authentication and file operations. These scripts are not included in the analyzed content, meaning their underlying logic and security cannot be verified.
  • [CREDENTIALS_UNSAFE]: The skill handles OAuth tokens for Google Workspace accounts with full read/write permissions. While it claims to store tokens in the system keyring, it also explicitly states it uses a 'cloud function' to refresh tokens. This architectural choice often indicates a proxy-based authentication flow where refresh tokens are sent to a developer-controlled endpoint, posing a risk of credential compromise.
  • [DATA_EXFILTRATION]: The reliance on an external cloud function for token management constitutes a potential data exfiltration vector. If the 'cloud function' is not an official Google API endpoint, it could be used to intercept OAuth refresh tokens, allowing persistent unauthorized access to the user's Google Drive data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 31, 2026, 04:34 PM
Security Audit — agent-trust-hub — google-drive-automation