Back to skill

Security audit

Health Data

Security checks across malware telemetry and agentic risk

Overview

The supplied scanner signals show no findings, but no target skill artifact was available in the workspace to independently verify behavior.

Treat this as a low-confidence pass based only on the clean SkillSpector result and pending VirusTotal telemetry. Before installing, review the actual skill files and metadata to confirm what it can access, what commands it asks the agent to run, and whether any credentials or long-running behavior are required.

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

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.