notebooklm-internal

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run extensively across multiple scripts (scripts/run.py, scripts/setup_environment.py, scripts/__init__.py) to manage a local Python virtual environment, install dependencies, and execute sub-scripts.
  • [COMMAND_EXECUTION]: In scripts/add_source.py and scripts/ensure_notebook.py, the skill executes a local framework script execution/cross_agent_context.py via subprocess.run to store telemetry and action logs within the vendor's (@techwavedev/agi-agent-kit) memory system.
  • [EXTERNAL_DOWNLOADS]: During the setup process in scripts/setup_environment.py and scripts/__init__.py, the skill downloads Python packages from official registries and browser binaries (Chrome/Chromium) via the patchright library for automation purposes.
  • [SAFE]: The skill manages Google authentication sessions using browser cookies stored locally in data/browser_state/state.json. This is standard practice for persistent browser automation and the data is restricted to the local skill directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:44 PM
Security Audit — agent-trust-hub — notebooklm-internal