Back to skill

Security audit

Skill Recommender

Security checks across malware telemetry and agentic risk

Overview

This skill coherently recommends and deduplicates local skills without hidden network access, persistence, credential use, or file mutation.

Installers should understand that the helper scripts read SKILL.md files from whatever skills directory they provide. Use it on skill collections you intend to analyze; there is no evidence here of data transmission, file modification, persistence, or credential use.

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.