ClawHub
Back to skill

Security audit

Nlm Cli

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent wrapper for a NotebookLM command-line tool; it can change or share notebook content, but those powers are disclosed and fit the stated purpose.

Install only if you trust the external notebooklm-mcp-cli package and intend to let it operate through your NotebookLM or Google session. Before running share, invite, delete, source import/sync, download, MCP setup, or skill install commands, verify the active profile, target notebook, recipients, and sharing status.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/nlm.mjs:40