Back to skill

Security audit

hierarchical-coordinator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only project coordination skill, with no executable code, install hooks, credential access, or hidden persistence found.

Safe to install as a planning and coordination skill. When using it on sensitive projects, keep delegated agents scoped to the minimum needed context and require explicit human approval before purchases, crypto/payment activity, deployments, or broad code changes.

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

Static analysis

No suspicious patterns detected.