notebooklm

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a dedicated wrapper script (scripts/run.py) and setup scripts (scripts/setup_environment.py, scripts/__init__.py) to manage its execution environment. It uses subprocess.run and os.execv to install dependencies and execute internal Python scripts within an isolated virtual environment.
  • [EXTERNAL_DOWNLOADS]: During its first-time setup, the skill downloads required Python packages (patchright, python-dotenv) from official registries and installs the Google Chrome browser via the patchright library to ensure reliable automation.
  • [CREDENTIALS_UNSAFE]: To maintain authentication with Google services, the skill stores browser session cookies and state in a local data/ directory. The documentation explicitly identifies this as sensitive data and includes instructions to ensure it is not shared or committed to version control.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:52 PM
Security Audit — agent-trust-hub — notebooklm