Back to skill

Security audit

Judgment_Enhancement_Engine

Security checks across malware telemetry and agentic risk

Overview

This is a local decision-support helper with no evidence of hidden network access, credential handling, persistence, or destructive behavior.

Reasonable to install as a local Python decision-support library. Review the setup script before running it, treat its selected action as advice rather than authorization to act, and avoid placing secrets or sensitive labels in states/actions if you record outcome history.

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