Back to skill

Security audit

Skill Vetter — Security Audit for AI Skills

Security checks across malware telemetry and agentic risk

Overview

This is a security-review checklist skill with no executable code, hidden persistence, or automatic access to private data.

Reasonable to install as a checklist aid. Verify the publisher/source before relying on it for security decisions, and only run the GitHub curl examples when you intentionally want the agent to inspect that repository.

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.