ClawHub
Back to skill

Security audit

Claude Agent Team Workflows 0.1.0

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed multi-agent orchestration helper, with a broad trigger description but no artifact-backed evidence of persistence, exfiltration, destructive actions, or hidden behavior.

Before installing, understand that this skill may be invoked for a wide range of multi-agent coordination requests. Use it when you explicitly want an agent team workflow, and review any proposed agents, delegated tasks, or commands before execution.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says to use the skill when the user asks to 'run a team workflow, create an agent team, or coordinate parallel work across multiple teammates — for any domain.' This is a very broad activation scope without clear boundaries or negative examples, increasing the chance of unintended invocation for generic collaboration or planning requests.

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: agent-team-workflows
description: "Universal multi-agent workflow orchestration using Claude Code Agent Teams. Use when user asks to run a team workflow, create an agent team, or coordinate parallel work across multiple teammates — for any domain (software, content, data, strategy, research, etc.)."
---

# Agent Team Workflows
Confidence
60% confidence
Finding
create an agent team, or coordinate parallel work across multiple teammates — for any domain (software, content, data, strategy, research, etc.)." --- # Agent Team Workflows Universal orchestration

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.