notebook-lm

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the notebooklm-py package from PyPI and the playwright browser tool to function (SKILL.md, references/auth.md). These are external dependencies used for the skill's primary purpose of automating Google NotebookLM.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its data ingestion capabilities.\n
  • Ingestion points: The agent can import content from external URLs, local files (PDF, txt, md, docx), and Google Drive documents (SKILL.md, references/workflows.md).\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are provided in the documentation to mitigate malicious content in sources.\n
  • Capability inventory: The skill includes powerful capabilities such as deleting notebooks (client.notebooks.delete), performing web research (client.research.start), and downloading generated files to the local system (client.artifacts.download_*) (SKILL.md, references/workflows.md).\n
  • Sanitization: There is no evidence of content sanitization or validation before the data is processed by the AI service.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 05:47 AM
Security Audit — agent-trust-hub — notebook-lm