Back to skill

Security audit

NPM Search

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a simple npm search helper, and the only concern is an unverified local helper script noted by telemetry rather than confirmed malicious behavior.

Before installing, check that the package actually includes `scripts/npmsearch` and skim it for unexpected file access, credential handling, or network calls outside npm/package metadata lookup. The available signals do not show malicious behavior, but the helper script should be visible and understandable because the skill asks the agent to execute it.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.