Master Orchestrator

Security checks across malware telemetry and agentic risk

Overview

This skill only changes how the assistant organizes answers through simulated expert roles and does not request code execution, credentials, file access, persistence, or hidden system changes.

Install this if you want the assistant to route answers through simulated expert roles. Be aware that it may answer in Chinese or use Chinese role labels unless you ask otherwise, and treat sensitive legal, financial, security, immigration, or investment guidance as ordinary AI output that should be independently verified.

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
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill content defines its role and workflow entirely in Chinese and does not provide a user-language choice or a documented reason for restricting output locale. In an orchestration skill, this can cause user confusion, misrouting, or unsafe misunderstanding of delegated advice when users expect another language, especially for security, legal, or financial topics.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal