notebooklm

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents installation from a GitHub repository (github.com/PleasePrompto/notebooklm-skill) and a skill registry (github.com/akillness/jeo-skills). These references are consistent with the skill's documented installation process and the author's identity.
  • [COMMAND_EXECUTION]: The skill uses local shell commands to execute Python scripts for browser automation tasks, such as authentication management and notebook queries. These commands are transparently documented in the SKILL.md and are required for the skill's core functionality.
  • [CREDENTIALS_UNSAFE]: The skill documentation correctly identifies that sensitive data (cookies, local storage, browser profile) is stored locally at ~/.claude/skills/notebooklm/data/. This follows best practices for local automation by avoiding hardcoded secrets and instructing users to use .env files or manual login for session management.
  • [DATA_EXFILTRATION]: While the skill performs network operations to reach notebooklm.google.com, this is the intended primary purpose of the skill. No patterns of exfiltrating local sensitive files (like SSH keys or AWS credentials) were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 11:38 AM
Security Audit — agent-trust-hub — notebooklm