Back to skill

Security audit

TRIGGERcmd

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly scoped TRIGGERcmd connector that can trigger user-configured remote commands, with that authority disclosed and gated by confirmation for write actions.

Install only if you intend this agent to operate TRIGGERcmd through your OOMOL-connected account. Treat trigger_command as remote command execution on your configured machines: review the target computer, command name, and parameters before approving any write action, and verify the oo CLI installer before first-time setup.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.