# AutoPentester

**Repository Path**: frontcold/AutoPentester

## Basic Information

- **Project Name**: AutoPentester
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-02-01
- **Last Updated**: 2026-02-01

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# AutoPentester: An LLM Agent-based Framework for Automated Pentesting

![](https://img.shields.io/badge/license-MIT-000000.svg)
[![arXiv](https://img.shields.io/badge/arXiv-1909.05658-<color>.svg)]()

**Note:**
- If you are using this work for academic purposes, please cite our [paper](https://arxiv.org/abs/2510.05605).
- If you find any <font color='red'>incorrect</font> / <font color='red'>inappropriate</font> / <font color='red'>outdated</font> content, please kindly consider opening an issue or a PR.

### Updates
- This work has been accepted for the IEEE TrustCom 2025.
  
<div align="center">
<a href="https://drive.google.com/file/d/1HSCEOYl-C5L1nwaYur1a8TgI8MBI04ev/view?usp=drive_link">
    <img src="/framework.png" width="850" height="450" alt="overall architecure"/>
</a>
</div>

<!-- Quick Start -->
## Installation
1. Create a virtual environment. (`python3 -m venv myenv`, `source myenv/bin/activate`)
2. Clone the project and install the requirements.
     - `git clone <repo_url>`
     - `cd AutoPentester`
     - Create a virtual environment with Python pip3 3.12.3. Then install the requirements.txt inside it.
     - `pip3 install -r requirements.txt`
     - `pip3 install -e .`
3. To use OpenAI API
   - **Ensure that you have link a payment method to your OpenAI account.**
   - export your API key with `export OPENAI_API_KEY="<your key here>"`
4. To run the framework, type  `pentestgpt --loggin`
5. You will be asked for your OpenAI key and the IP address.
6. Do you want to continue from previous session? (y/n) -> Press n
7. Give a pentesting task. You can use a prompt like "I want to test the machine with the IP (targe_IP)"
8. Only for the first run, it will take 10 minutes to build the vectorbase of the RAG module at the beginning. Please wait until it starts its process.


### Demo
Please find the demonstration video in the following [link](https://drive.google.com/file/d/1BPLcEHJaLIunENIeK0sOpBFylrpOZdHA/view?usp=sharing).

### Log files
The processed log files are in the processed_log_files directory.
The quantitative results were calculated baseed on these log files.

### Survey analysis
The analysis of the survey is in the Survey_analysis directory.
Run the analysis.py to plot the graphs.

# Citations
If you are using this work for academic purposes, please cite our [paper](https://arxiv.org/abs/2510.05605).
```
@article{ginige2025autopentester,
  title={AutoPentester: An LLM Agent-based Framework for Automated Pentesting},
  author={Ginige, Yasod and Niroshan, Akila and Jain, Sajal and Seneviratne, Suranga},
  journal={arXiv preprint arXiv:2510.05605},
  year={2025}
}
```