notebooklm

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection through its data retrieval and processing workflows.\n
  • Ingestion points: Untrusted data enters the agent context through source_add (URLs, Google Drive documents, local files) and research_import.\n
  • Boundary markers: There are no specific delimiters or guardrail instructions defined in the rules to prevent the agent from accidentally following instructions embedded in the retrieved content.\n
  • Capability inventory: The skill grants the agent access to powerful tools including Bash, Write, Edit, and TaskCreate.\n
  • Sanitization: The skill documentation does not describe any sanitization or validation of the content fetched from external sources.\n- [EXTERNAL_DOWNLOADS]: The skill relies on the third-party Python package notebooklm-mcp-cli from PyPI as a core dependency for its operations.\n- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute nlm CLI commands for authentication, configuration, and interacting with the NotebookLM service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 01:41 AM