notebooklm

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a central wrapper script and an environment setup script that execute subprocesses to create a Python virtual environment, install dependencies, and run automation tasks within the skill's local directory.- [EXTERNAL_DOWNLOADS]: The skill downloads required Python packages from the official registry and uses the patchright utility to install a browser engine, which is necessary for automating the NotebookLM web interface.- [PROMPT_INJECTION]: The skill retrieves text from an external web platform and provides instructions for the agent to analyze this content and perform follow-up queries. While this creates a surface for indirect prompt injection, it is a standard behavior for research-oriented skills and is subject to the agent's core safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:49 AM
Security Audit — agent-trust-hub — notebooklm