PentestGPT
Automated Penetration Testing Agentic Framework Powered by Large Language Models
Install / Use
/learn @GreyDGL/PentestGPTREADME
<a name="readme-top"></a>
<!-- PROJECT SHIELDS -->
[![Discord][discord-shield]][discord-url]
<a href="https://trendshift.io/repositories/3770" target="_blank"><img src="https://trendshift.io/api/badge/repositories/3770" alt="GreyDGL%2FPentestGPT | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
Demo
Installation
PentestGPT in Action
What's New in v1.0 (Agentic Upgrade)
- Autonomous Agent - Agentic pipeline for intelligent, autonomous penetration testing
- Session Persistence - Save and resume penetration testing sessions
- Docker-First - Isolated, reproducible environment with security tools pre-installed
In Progress: Multi-model support for OpenAI, Gemini, and other LLM providers
Features
- AI-Powered Challenge Solver - Leverages LLM advanced reasoning to perform penetration testing and CTFs
- Live Walkthrough - Tracks steps in real-time as the agent works through challenges
- Multi-Category Support - Web, Crypto, Reversing, Forensics, PWN, Privilege Escalation
- Real-Time Feedback - Watch the AI work with live activity updates
- Extensible Architecture - Clean, modular design ready for future enhancements
Quick Start
Prerequisites
- Docker (required) - Install Docker
- LLM Provider (choose one):
- Anthropic API Key from console.anthropic.com
- Claude OAuth Login (requires Claude subscription)
- OpenRouter for alternative models at openrouter.ai
- Tutorial: Using Local Models with Claude Code
Installation
# Clone and build
git clone --recurse-submodules https://github.com/GreyDGL/PentestGPT.git
cd PentestGPT
make install
# Configure authentication (first time only)
make config
# Connect to container
make connect
Note: The
--recurse-submodulesflag downloads the benchmark suite. If you already cloned without it, run:git submodule update --init --recursive
Try a Benchmark
cd benchmark/standalone-xbow-benchmark-runner
python3 run_benchmarks.py --range 1-1 --pattern-flag
See Benchmark Documentation for detailed usage.
Commands Reference
| Command | Description |
|---------|-------------|
| make install | Build the Docker image |
| make config | Configure API key (first-time setup) |
| make connect | Connect to container (main entry point) |
| make stop | Stop container (config persists) |
| make clean-docker | Remove everything including config |
Usage
# Interactive TUI mode (default)
pentestgpt --target 10.10.11.234
# Non-interactive mode
pentestgpt --target 10.10.11.100 --non-interactive
# With challenge context
pentestgpt --target 10.10.11.50 --instruction "WordPress site, focus on plugin vulnerabilities"
Keyboard Shortcuts: F1 Help | Ctrl+P Pause/Resume | Ctrl+Q Quit
Using Local LLMs
PentestGPT supports routing requests to local LLM servers (LM Studio, Ollama, text-generation-webui, etc.) running on your host machine.
Prerequisites
- Local LLM server with an OpenAI-compatible API endpoint
- LM Studio: Enable server mode (default port 1234)
- Ollama: Run
ollama serve(default port 11434)
Setup
# Configure PentestGPT for local LLM
make config
# Select option 4: Local LLM
# Start your local LLM server on the host machine
# Then connect to the container
make connect
Customizing Models
Edit scripts/ccr-config-template.json to customize:
localLLM.api_base_url: Your LLM server URL (default:host.docker.internal:1234)localLLM.models: Available model names on your server- Router section: Which models handle which operations
| Route | Purpose | Default Model |
|-------|---------|---------------|
| default | General tasks | openai/gpt-oss-20b |
| background | Background operations | openai/gpt-oss-20b |
| think | Reasoning-heavy tasks | qwen/qwen3-coder-30b |
| longContext | Large context handling | qwen/qwen3-coder-30b |
| webSearch | Web search operations | openai/gpt-oss-20b |
Troubleshooting
- Connection refused: Ensure your LLM server is running and listening on the configured port
- Docker networking: Use
host.docker.internal(notlocalhost) to access host services from Docker - Check CCR logs: Inside the container, run
cat /tmp/ccr.log
Telemetry
PentestGPT collects anonymous usage data to help improve the tool. This data is sent to our Langfuse project and includes:
- Session metadata (target type, duration, completion status)
- Tool execution patterns (which tools are used, not the actual commands)
- Flag detection events (that a flag was found, not the flag content)
No sensitive data is collected - command outputs, credentials, or actual flag values are never transmitted.
Opting Out
# Via command line flag
pentestgpt --target 10.10.11.234 --no-telemetry
# Via environment variable
export LANGFUSE_ENABLED=false
Benchmarks
PentestGPT includes 104 XBOW validation benchmarks for comprehensive testing and evaluation.
cd benchmark/standalone-xbow-benchmark-runner
python3 run_benchmarks.py --range 1-10 --pattern-flag # Run benchmarks 1-10
python3 run_benchmarks.py --all --pattern-flag # Run all 104 benchmarks
python3 run_benchmarks.py --retry-failed # Retry failed benchmarks
python3 run_benchmarks.py --dry-run --range 1-5 # Preview without executing
Performance Highlights
PentestGPT achieved an 86.5% success rate (90/104 benchmarks) on the XBOW validation suite:
- Cost: Average $1.11, Median $0.42 per successful benchmark
- Time: Average 6.1 minutes, Median 3.3 minutes per successful benchmark
- Success rates by difficulty:
- Level 1: 91.1%
- Level 2: 74.5%
- Level 3: 62.5%
For detailed benchmark results, analysis, and automated testing instructions, see the Benchmark Documentation.
Legacy Version
The previous multi-LLM version (v0.15) supporting OpenAI, Gemini, Deepseek, and Ollama is archived in legacy/:
cd legacy && pip install -e . && pentestgpt --reasoning gpt-4o
Citation
If you use PentestGPT in your research, please cite our paper:
@inproceedings{299699,
author = {Gelei Deng and Yi Liu and Víctor Mayoral-Vilches and Peng Liu and Yuekang Li and Yuan Xu and Tianwei Zhang and Yang Liu and Martin Pinzger and Stefan Rass},
title = {{PentestGPT}: Evaluating and Harnessing Large Language Models for Automated Penetration Testing},
booktitle = {33rd USENIX Security Symposium (USENIX Security 24)},
year = {2024},
isbn = {978-1-939133-44-1},
address = {Philadelphia, PA},
pages = {847--864},
url = {https://www.usenix.org/conference/usenixsecurity24/presentation/deng},
publisher = {USENIX Association},
month = aug
}
License
Distributed under the MIT License. See LICENSE.md for more information.
Disclaimer: This tool is for educational purposes and authorized security testing only. The authors do not condone any illegal use. Use at your own risk.
Acknowledgments
- Research supported by Quantstamp and NTU Singapore
