ClawHub
Back to skill

Security audit

Claude Agent Team Workflows 0.1.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent guide for running Claude Code agent-team workflows, with one notable setup step that enables Agent Teams globally in the user's Claude settings.

Install this only if you intentionally use Claude Code Agent Teams and are comfortable enabling the experimental Agent Teams flag in your global Claude settings. Use it for explicit team workflows, confirm cost and scope before spawning teammates, and avoid sharing sensitive inputs with teammates unless that is intended for the task.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Agent Config Directory Access

High
Category
Agent Snooping
Content
## Prerequisites

Agent Teams must be enabled. Add to `~/.claude/settings.json`:

```json
{
Confidence
90% confidence
Finding
The skill instructs users to modify ~/.claude/settings.json, which is a sensitive agent configuration location affecting broader runtime behavior beyond this skill. Directing changes to global config can expand capabilities for future sessions and other skills, increasing the blast radius if misused or if users enable experimental features without understanding the security implications.

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
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill advertises itself as applicable to 'any domain' and for broadly phrased requests like creating a team or coordinating parallel work, which makes accidental triggering likely on many ordinary user tasks. In an orchestration skill, overbroad activation is risky because it can cause unnecessary multi-agent spawning, broaden access to context and files, and increase cost and operational surface without clear user intent.

Static analysis

No suspicious patterns detected.