Back to skill

Security audit

URL Toolkit

Security checks across malware telemetry and agentic risk

Overview

The available scan evidence does not show malicious or suspicious behavior, but target-specific artifact files were not clearly available for deeper verification.

This appears acceptable based on the supplied scan context, but because VirusTotal is pending and the target artifact was not clearly exposed for full local inspection, review the actual SKILL.md and metadata before installing, especially for any requested credentials, command execution, or broad local access.

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

No suspicious patterns detected.