notebooklm
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the
notebooklm-pypackage from PyPI or its official GitHub repository. These are standard and trusted software distribution platforms. - [COMMAND_EXECUTION]: The skill uses shell commands for installation and provides a mechanism for session recovery via user-defined scripts. These operations are standard practices for an automation library.
- [DATA_EXFILTRATION]: The library manages sensitive Google session cookies required for authentication. These are stored locally in the user's home directory with restricted file permissions (0o600). The analysis found no evidence of data being sent to untrusted third-party domains.
- [PROMPT_INJECTION]: The instructions provided for the AI agent are standard for a tool-based skill and do not contain any patterns attempting to override AI behavior or bypass safety filters.
Audit Metadata