Agent Team Orchestration

Security checks across malware telemetry and agentic risk

Overview

This is a simple planning template for organizing multi-agent work, with no executable code or hidden system access.

Safe to install as a planning aid. When using it, keep any shared state files inside the relevant project, avoid storing secrets or private credentials in handoff briefs, and review persistent context before later agents reuse it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list includes generic phrases like "set up agents" and "agent coordination," which can match many ordinary user requests and cause this skill to activate unexpectedly. Over-broad activation increases the chance that orchestration behavior is injected into unrelated workflows, potentially altering task routing, context sharing, or review behavior without the user's clear intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal