nlm-skill

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the nlm CLI tool to perform its operations. It instructs the agent to run commands via Bash to manage notebooks, add sources, and generate content.
  • [EXTERNAL_DOWNLOADS]: The skill documentation guides the user to install the notebooklm-mcp-cli package using the uv tool. This package is maintained by the skill author and is required for the intended functionality.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from various external sources.
  • Ingestion points: Content is ingested from web URLs, YouTube transcripts, and Google Drive documents as described in SKILL.md and references/workflows.md.
  • Boundary markers: Absent; the instructions do not specify delimiters or provide guidance for the agent to ignore instructions embedded within external source material.
  • Capability inventory: The skill possesses capabilities for file management, notebook manipulation, and content generation through tool calls and Bash execution.
  • Sanitization: Absent; there is no mention of sanitizing or filtering external content before it is added to a notebook or used for generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 04:31 AM