Back to skill

Security audit

1.2.0

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward incident-triage playbook with templates and echo-only helper scripts, with no evidence of hidden or harmful behavior.

Before installing, confirm that any local triage or workflow command used by your agent is the intended incident-management tool, and review owner or timeline updates before applying them during a real incident. The mismatched healthcheck output is worth noting but does not indicate harmful behavior.

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.