Multi Agent Coordinator Zhuyu28

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward multi-agent coordination helper that only stores local task/session state and shows no hidden network, credential, or destructive behavior.

Safe for ordinary coordination use. Before installing, remember that task descriptions and results can be saved in a local JSON file, so avoid putting secrets or sensitive personal data into sessions unless you control where that file is stored and clean it up when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal