YH

yenn503/hexstrike-redteam

Security testing
169 stars 0 forks Quality 61 Trend 46

AI-powered MCP penetration testing framework combining HexStrike's 150+ security tools with BOAZ's advanced payload evasion (77+ loaders, 12 encoders).

Overview

HexStrike now includes , an advanced payload evasion framework for red team operations: - - Syscall, stealth, memory guard, threadless, and VEH/VCH techniques - - AES, ChaCha20, UUID, XOR, MAC, RC4, and more - - API unhooking, ETW patching, LLVM obfuscation (Akira/Pluto) - - Anti-emulation checks, sleep obfuscation, entropy reduction - - Entropy analysis and optimization for heuristic evasion Payload with stealth injection techniques evading real-time protection and maintaining low detection profile Demonstrates BOAZ transforming standard MSFVenom payloads into sophisticated evasive binaries with: - (Standard stealth injection) - (Low entropy, legitimate-looking format) - (Event Tracing for Windows patching) - (Sandbox detection) - (Excellent for bypassing heuristic analysis) HexStrike AI MCP v6.0 features a multi-agent architecture with autonomous AI agents, intelligent decision-making, and vulnerability intelligence. 1.

README


🔥 BOAZ Red Team Integration

HexStrike now includes BOAZ, an advanced payload evasion framework for red team operations:

BOAZ Features

  • 77+ Process Injection Loaders - Syscall, stealth, memory guard, threadless, and VEH/VCH techniques
  • 12 Encoding Schemes - AES, ChaCha20, UUID, XOR, MAC, RC4, and more
  • EDR/AV Evasion - API unhooking, ETW patching, LLVM obfuscation (Akira/Pluto)
  • Anti-Analysis - Anti-emulation checks, sleep obfuscation, entropy reduction
  • Binary Analysis - Entropy analysis and optimization for heuristic evasion

BOAZ Capabilities in Action


Architecture Overview

HexStrike AI MCP v6.0 features a multi-agent architecture with autonomous AI agents, intelligent decision-making, and vulnerability intelligence.

%%{init: {"themeVariables": {
  "primaryColor": "#b71c1c",
  "secondaryColor": "#ff5252",
  "tertiaryColor": "#ff8a80",
  "background": "#2d0000",
  "edgeLabelBackground":"#b71c1c",
  "fontFamily": "monospace",
  "fontSize": "16px",
  "fontColor": "#fffde7",
  "nodeTextColor": "#fffde7"
}}}%%
graph TD
    A[AI Agent - Claude/GPT/Copilot] -->|MCP Protocol| B[HexStrike MCP Server v6.0]

    B --> C[Intelligent Decision Engine]
    B --> D[12+ Autonomous AI Agents]
    B --> E[Modern Visual Engine]
    B --> BOAZ[BOAZ Payload Engine]

    C --> F[Tool Selection AI]
    C --> G[Parameter Optimization]
    C --> H[Attack Chain Discovery]

    D --> I[BugBounty Agent]
    D --> J[CTF Solver Agent]
    D --> K[CVE Intelligence Agent]
    D --> L[Exploit Generator Agent]

    E --> M[Real-time Dashboards]
    E --> N[Progress Visualization]
    E --> O[Vulnerability Cards]

    BOAZ --> BOAZ1[77+ Process Injection Loaders]
    BOAZ --> BOAZ2[12 Encoding Schemes]
    BOAZ --> BOAZ3[EDR/AV Evasion]
    BOAZ1 --> BOAZ4[Syscall/Stealth/Threadless]
    BOAZ2 --> BOAZ5[AES/ChaCha20/UUID/XOR]
    BOAZ3 --> BOAZ6[API Unhooking/ETW Patching]

    B --> P[127 Security Tools - 53 Auto-Installed]
    P --> Q[Network Tools - 10]
    P --> R[Web App Tools - 19]
    P --> S[Cloud Tools - 10]
    P --> T[Binary Tools - 13]
    P --> U[CTF Tools - 10]
    P --> V[OSINT Tools - 13]

    B --> W[Advanced Process Management]
    W --> X[Smart Caching]
    W --> Y[Resource Optimization]
    W --> Z[Error Recovery]

    style A fill:#b71c1c,stroke:#ff5252,stroke-width:3px,color:#fffde7
    style B fill:#ff5252,stroke:#b71c1c,stroke-width:4px,color:#fffde7
    style C fill:#ff8a80,stroke:#b71c1c,stroke-width:2px,color:#fffde7
    style D fill:#ff8a80,stroke:#b71c1c,stroke-width:2px,color:#fffde7
    style E fill:#ff8a80,stroke:#b71c1c,stroke-width:2px,color:#fffde7
    style BOAZ fill:#d32f2f,stroke:#b71c1c,stroke-width:3px,color:#fffde7

How It Works

  1. AI Agent Connection - Claude, GPT, or other MCP-compatible agents connect via FastMCP protocol
  2. Intelligent Analysis - Decision engine analyzes targets and selects optimal testing strategies
  3. Autonomous Execution - AI agents execute comprehensive security assessments using 150+ tools
  4. Real-time Adaptation - System adapts based on results and discovered vulnerabilities
  5. BOAZ Payload Generation - Advanced payload evasion with 77+ loaders, 12 encoders, and EDR/AV bypass
  6. Advanced Reporting - Visual output with vulnerability cards and risk analysis

Installation

Quick Setup to Run the hexstrike MCPs Server

# 1. Clone the repository
git clone https://github.com/Yenn503/Hexstrike-redteam.git hexstrike-ai
cd hexstrike-ai

# 2. Create virtual environment
python3 -m venv hexstrike-env
source hexstrike-env/bin/activate  # Linux/Mac
# hexstrike-env\Scripts\activate   # Windows

# 3. Install Python dependencies
pip3 install -r requirements.txt

# 4. **REQUIRED: Install BOAZ system dependencies**
# This step is MANDATORY for BOAZ payload generation to work
# Installs MinGW, NASM, Wine, LLVM obfuscators (Akira/Pluto), and build tools
cd BOAZ_beta
bash requirements.sh
cd ..

# The script will:
# - Install MinGW cross-compiler (x86_64-w64-mingw32-g++)
# - Install NASM assembler
# - Install Wine (for testing Windows binaries)
# - Build Akira LLVM obfuscator (~30 min compile time)
# - Build Pluto LLVM obfuscator (~20 min compile time)
# - Install signature tools (Mangle, pyMetaTwin)
# - Install SysWhispers2 for syscall generation
# **Note:** This may take a while depending on your system. Answer 'y' when prompted.

Installation and Setting Up Guide for various AI Clients:

Installation & Demo Video

Watch the full installation and setup walkthrough here: YouTube - HexStrike AI Installation & Demo

Supported AI Clients for Running & Integration

You can install and run HexStrike AI MCPs with various AI clients, including:

  • 5ire (Latest version v0.14.0 not supported for now)
  • VS Code Copilot
  • Roo Code
  • Cursor
  • Claude Desktop
  • Any MCP-compatible agent

Refer to the video above for step-by-step instructions and integration examples for these platforms.

Install Security Tools

Automated Installation (Recommended):

Run the installation script to automatically install 53 essential security tools:

cd install
sudo ./install_all.sh

This installs:

  • System dependencies (MinGW, Wine, NASM, build tools)
  • 70+ security tools (53 currently working, see breakdown below)
  • Python virtual environment with all dependencies
  • BOAZ LLVM obfuscators (Akira + Pluto)
  • MCP configuration for Claude Desktop/CLI

What Gets Auto-Installed (53 Tools):

Tools Requiring Manual Installation (74 tools):

Some specialized tools require manual installation due to licensing, dependencies, or system requirements:

  • Wireless: aircrack-ng suite, kismet, wireshark, tshark
  • Cloud: kube-hunter, kube-bench, scout-suite, checkov, terrascan, falco, clair
  • Web: dirsearch, dirb, burp suite, zaproxy, jaeles, x8, wfuzz, xsser
  • Password: medusa, patator, crackmapexec, ophcrack, hashcat-utils, hashpump
  • Binary: ropper, libc-database
  • OSINT: maltego, censys-cli, have-i-been-pwned, social-analyzer
  • Network: arp-scan, nbtscan, rpcclient, smbmap, enum4linux (classic), fierce, dnsenum, tshark
  • API: insomnia, postman, httpie
  • Forensics: autopsy, bulk-extractor, outguess
  • Additional: qsreplace, uro

Installation Notes:

  • Installation script works on any Linux system (portable paths)
  • No hardcoded user paths - works for all users
  • Some tools may fail on certain distributions (fallbacks included)
  • Full installation takes ~60-90 minutes (LLVM compilation)
  • Requires ~24GB disk space
  • See install/README.md for troubleshooting

Browser Agent Requirements:

# Chrome/Chromium for Browser Agent
sudo apt install chromium-browser chromium-chromedriver
# OR install Google Chrome
wget -q -O - https://dl.google.com/linux/linux_signing_key.pub | sudo apt-key add -
echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" | sudo tee /etc/apt/sources.list.d/google-chrome.list
sudo apt update && sudo apt install google-chrome-stable

Start the Server

# Start the MCP server
python3 hexstrike_server.py

# Optional: Start with debug mode
python3 hexstrike_server.py --debug

# Optional: Custom port configuration
python3 hexstrike_server.py --port 8888

Verify Installation

# Test server health
curl http://localhost:8888/health

# Test AI agent capabilities
curl -X POST http://localhost:8888/api/intelligence/analyze-target \
  -H "Content-Type: application/json" \
  -d '{"target": "example.com", "analysis_type": "comprehensive"}'

AI Client Integration Setup

Claude Desktop Integration or Cursor

Edit ~/.config/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "hexstrike-ai": {
      "command": "python3",
      "args": [
        "/path/to/hexstrike-ai/hexstrike_mcp.py",
        "--server",
        "http://localhost:8888"
      ],
      "description": "HexStrike AI v6.0 - Advanced Cybersecurity Automation Platform",
      "timeout": 300,
      "disabled": false
    }
  }
}

VS Code Copilot Integration

Configure VS Code settings in .vscode/settings.json:

{
  "servers": {
    "hexstrike": {
      "type": "stdio",
      "command": "python3",
      "args": [
        "/path/to/hexstrike-ai/hexstrike_mcp.py",
        "--server",
        "http://localhost:8888"
      ]
    }
  },
  "inputs": []
}

BOAZ Capabilities in Action

View this README on GitHub

Install

This server does not publish a one-line install command.

Open the repository installation guide

Configuration

{ "mcpServers": { "hexstrike-ai": { "command": "python3", "args": [ "/path/to/hexstrike-ai/hexstrike_mcp.py", "--server", "http://localhost:8888" ], "description": "HexStrike AI v6.0 - Advanced Cybersecurity Automation Platform", "timeout": 300, "disabled": false } } }