RedTeam-Agent
AI-Powered Autonomous Red Team Framework
Let AI become your security audit hacker
English | 简体中文 | Documentation | Quick Start
Overview
RedTeam-Agent is an AI-powered red team framework using a skill-first terminal workflow. AI reads project skills, discovers tools, executes commands in terminal, and summarizes high-signal findings.
Core philosophy: no manual tool-by-tool operation. Let AI orchestrate the workflow end-to-end.
Key Features
- Plug and play: 15+ tools with automated setup
- AI-driven workflow: Skill + terminal execution
- Token optimized: output filtering and file-first strategy
- AD coverage: BloodHound + impacket + Responder chain
- Multi-client support: Cursor, Claude Desktop, VS Code/Cline
Tool Matrix
Network
- gogo: fast asset discovery
- fscan: comprehensive host/service scan
Web
- httpx: HTTP probing and fingerprinting
- nuclei: template-based vulnerability validation
- ffuf: directory and parameter fuzzing
Active Directory
- SharpHound / bloodhound-python
- impacket (GetNPUsers, GetUserSPNs, secretsdump, ntlmrelayx, etc.)
- pywerview, ldapdomaindump
Lateral Movement
- nxc (NetExec)
- impacket-wmiexec
- impacket-psexec
Quick Start
1. Requirements
Python 3.8+
Windows 10/11 or Linux/macOS
8GB+ RAM recommended
2. Installation
git clone https://github.com/ktol1/RedTeam-Agent.git
cd RedTeam-Agent
python -m venv venv
# Windows PowerShell
.\venv\Scripts\Activate.ps1
# Linux/macOS
source venv/bin/activate
# Windows
python scripts/install_tools.py
# Linux/macOS
python scripts/install_tools_linux.py
3. Enable Skills Terminal Mode
No extra server setup is required.
cd RedTeam-Agent
dir .\tools
AI will read the repository skill and .github/copilot-instructions.md, then execute terminal commands directly.
4. Example Prompts
First load the redteam skill, then scan 192.168.1.0/24 in terminal,
write output to scan.txt, and summarize high-value findings.
Use SharpHound to collect corp.local data and summarize attack paths.
Set up a chisel proxy and provide upload/run commands.
AD Attack Flow
- Recon: gogo / fscan / kerbrute / pywerview
- Collection: SharpHound or bloodhound-python
- Analysis: BloodHound GUI or scripts/bloodhound_analysis.py
- Attack: Kerberoast / AS-REP Roast / secretsdump / relay
- Lateral: nxc / wmiexec / psexec / getST
Terminal Commands (Skill-driven)
Output Optimization
- Remove ANSI colors
- Compress blank lines
- Truncate excessive output
- Prefer file-first output for large scans
- Summarize only high-signal findings
Documentation
Contributing
Issues and pull requests are welcome.
MIT License - Copyright (c) 2024-2026 ktol1