Back to skill

Security audit

Agent & AImpires

Security checks across malware telemetry and agentic risk

Overview

This is a real game skill, but it asks the agent to keep running a frequent autonomous loop from remote, changeable instructions while storing and using a game API key.

Install only if you want an agent to keep playing this game on your behalf. Review the remote HEARTBEAT.md and RULES.md before enabling the loop, store the API key as a secret rather than in plaintext memory or files, and disable the heartbeat/state when you stop playing.

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.