GreyDGL/PentestGPT
Fork: 896 Star: 7351 (更新于 2024-12-11 10:26:41)
license: MIT
Language: Python .
A GPT-empowered penetration testing tool
最后发布版本: v0.14.0 ( 2024-05-15 16:27:08)
PentestGPT
A GPT-empowered penetration testing tool.
Explore the docs »
Design Details
·
View Demo
·
Report Bug or Request Feature
General Updates
- [Update on 25/10/2024] We're completing the refactoring of PentestGPT and will release v1.0 soon!
- [Update on 12/08/2024] The research paper on PentestGPT is published at USENIX Security 2024
- [Update on 25/03/2024] We're working on the next version of PentestGPT, with online searching, RAGs and more powerful prompting. Stay tuned!
- [Update on 17/11/2023] GPTs for PentestGPT is out! Check this: https://chat.openai.com/g/g-4MHbTepWO-pentestgpt
- [Update on 07/11/2023] GPT-4-turbo is out! Update the default API usage to GPT-4-turbo.
- Available videos:
- The latest installation video is here.
- PentestGPT for OSCP-like machine: HTB-Jarvis. This is the first part only, and I'll complete the rest when I have time.
- PentestGPT on HTB-Lame. This is an easy machine, but it shows you how PentestGPT skipped the rabbit hole and worked on other potential vulnerabilities.
- We're testing PentestGPT on HackTheBox. You may follow this link. More details will be released soon.
- Feel free to join the Discord Channel for more updates and share your ideas!
Quick Start
- Create a virtual environment if necessary. (
virtualenv -p python3 venv
,source venv/bin/activate
) - Install the project with
pip3 install git+https://github.com/GreyDGL/PentestGPT
-
Ensure that you have link a payment method to your OpenAI account. Export your API key with
export OPENAI_API_KEY='<your key here>'
,export API base withexport OPENAI_BASEURL='https://api.xxxx.xxx/v1'
if you need. - Test the connection with
pentestgpt-connection
- For Kali Users: use
tmux
as terminal environment. You can do so by simply runtmux
in the native terminal. - To start:
pentestgpt --logging
Getting Started
- PentestGPT is a penetration testing tool empowered by ChatGPT.
- It is designed to automate the penetration testing process. It is built on top of ChatGPT and operate in an interactive mode to guide penetration testers in both overall progress and specific operations.
-
PentestGPT is able to solve easy to medium HackTheBox machines, and other CTF challenges. You can check this example in
resources
where we use it to solve HackTheBox challenge TEMPLATED (web challenge). - A sample testing process of PentestGPT on a target VulnHub machine (Hackable II) is available at here.
- A sample usage video is below: (or available here: Demo)
Common Questions
-
Q: What is PentestGPT?
- A: PentestGPT is a penetration testing tool empowered by Large Language Models (LLMs). It is designed to automate the penetration testing process. It is built on top of ChatGPT API and operate in an interactive mode to guide penetration testers in both overall progress and specific operations.
-
Q: Do I need to pay to use PentestGPT?
- A: Yes in order to achieve the best performance. In general, you can use any LLMs you want, but you're recommended to use GPT-4 API, for which you have to link a payment method to OpenAI.
-
Q: Why GPT-4?
- A: After empirical evaluation, we find that GPT-4 performs better than GPT-3.5 and other LLMs in terms of penetration testing reasoning. In fact, GPT-3.5 leads to failed test in simple tasks.
-
Q: Why not just use GPT-4 directly?
- A: We found that GPT-4 suffers from losses of context as test goes deeper. It is essential to maintain a "test status awareness" in this process. You may check the PentestGPT Arxiv Paper for details.
-
Q: Can I use local GPT models?
- A: Yes. We support local LLMs with custom parser. Look at examples here.
Installation
PentestGPT is tested under Python 3.10
. Other Python3 versions should work but are not tested.
Install with pip
PentestGPT relies on OpenAI API to achieve high-quality reasoning. You may refer to the installation video here.
- Install the latest version with
pip3 install git+https://github.com/GreyDGL/PentestGPT
- You may also clone the project to local environment and install for better customization and development
-
git clone https://github.com/GreyDGL/PentestGPT
-
cd PentestGPT
-
pip3 install -e .
-
- You may also clone the project to local environment and install for better customization and development
- 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>'
- export API base with
export OPENAI_BASEURL='https://api.xxxx.xxx/v1'
if you need. - Test the connection with
pentestgpt-connection
- To verify that the connection is configured properly, you may run
pentestgpt-connection
. After a while, you should see some sample conversation with ChatGPT.- A sample output is below
You're testing the connection for PentestGPT v 0.11.0 #### Test connection for OpenAI api (GPT-4) 1. You're connected with OpenAI API. You have GPT-4 access. To start PentestGPT, please use <pentestgpt --reasoning_model=gpt-4> #### Test connection for OpenAI api (GPT-3.5) 2. You're connected with OpenAI API. You have GPT-3.5 access. To start PentestGPT, please use <pentestgpt --reasoning_model=gpt-3.5-turbo-16k>
- notice: if you have not linked a payment method to your OpenAI account, you will see error messages.
- The ChatGPT cookie solution is deprecated and not recommended. You may still use it by running
pentestgpt --reasoning_model=gpt-4 --useAPI=False
.
Build from Source
- Clone the repository to your local environment.
- Ensure that
poetry
is installed. If not, please refer to the poetry installation guide.
Usage
-
You are recommended to run:
- (recommended) -
pentestgpt --reasoning_model=gpt-4-turbo
to use the latest GPT-4-turbo API. -
pentestgpt --reasoning_model=gpt-4
if you have access to GPT-4 API. -
pentestgpt --reasoning_model=gpt-3.5-turbo-16k
if you only have access to GPT-3.5 API.
- (recommended) -
-
To start, run
pentestgpt --args
.-
--help
show the help message -
--reasoning_model
is the reasoning model you want to use. -
--parsing_model
is the parsing model you want to use. -
--useAPI
is whether you want to use OpenAI API. By default it is set toTrue
. -
--log_dir
is the customized log output directory. The location is a relative directory. -
--logging
defines if you would like to share the logs with us. By default it is set toFalse
.
-
-
The tool works similar to msfconsole. Follow the guidance to perform penetration testing.
-
In general, PentestGPT intakes commands similar to chatGPT. There are several basic commands.
- The commands are:
-
help
: show the help message. -
next
: key in the test execution result and get the next step. -
more
: let PentestGPT to explain more details of the current step. Also, a new sub-task solver will be created to guide the tester. -
todo
: show the todo list. -
discuss
: discuss with the PentestGPT. -
google
: search on Google. This function is still under development. -
quit
: exit the tool and save the output as log file (see the reporting section below).
-
- You can use <SHIFT + right arrow> to end your input (and <ENTER> is for next line).
- You may always use
TAB
to autocomplete the commands. - When you're given a drop-down selection list, you can use cursor or arrow key to navigate the list. Press
ENTER
to select the item. Similarly, use <SHIFT + right arrow> to confirm selection.
The user can submit info about:- tool: output of the security test tool used
- web: relevant content of a web page
- default: whatever you want, the tool will handle it
- user-comments: user comments about PentestGPT operations
- The commands are:
-
In the sub-task handler initiated by
more
, users can execute more commands to investigate into a specific problem:- The commands are:
-
help
: show the help message. -
brainstorm
: let PentestGPT brainstorm on the local task for all the possible solutions. -
discuss
: discuss with PentestGPT about this local task. -
google
: search on Google. This function is still under development. -
continue
: exit the subtask and continue the main testing session.
-
- The commands are:
Report and Logging
- [Update] If you would like us to collect the logs to improve the tool, please run
pentestgpt --logging
. We will only collect the LLM usage, without any information related to your OpenAI key. - After finishing the penetration testing, a report will be automatically generated in
logs
folder (if you quit withquit
command). - The report can be printed in a human-readable format by running
python3 utils/report_generator.py <log file>
. A sample reportsample_pentestGPT_log.txt
is also uploaded.
Custom Model Endpoints and Local LLMs
PentestGPT now support local LLMs, but the prompts are only optimized for GPT-4.
- To use local GPT4ALL model, you may run
pentestgpt --reasoning_model=gpt4all --parsing_model=gpt4all
. - To select the particular model you want to use with GPT4ALL, you may update the
module_mapping
class inpentestgpt/utils/APIs/module_import.py
. - You can also follow the examples of
module_import.py
,gpt4all.py
andchatgpt_api.py
to create API support for your own model.
Citation
Please cite our paper at:
@inproceedings {299699,
author = {Gelei Deng and Yi Liu and V{\'\i}ctor 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.txt
for more information.
The tool is for educational purpose only and the author does not condone any illegal use. Use as your own risk.
Contact the Contributors!
- Gelei Deng - - gelei.deng@ntu.edu.sg
- Víctor Mayoral Vilches - - v.mayoralv@gmail.com
- Yi Liu - yi009@e.ntu.edu.sg
- Peng Liu - liu_peng@i2r.a-star.edu.sg
- Yuekang Li - yuekang.li@unsw.edu.au
最近版本更新:(数据更新于 2024-10-07 23:01:06)
2024-05-15 16:27:08 v0.14.0
2024-05-14 18:03:01 v0.13.0
2023-07-26 00:40:42 v0.9.1
2023-05-12 21:46:03 v0.8
2023-05-01 23:58:26 v0.7.0
2023-04-30 22:56:06 v0.6.0
2023-04-26 23:29:17 v0.5.0
2023-04-22 17:45:21 v0.4.0
2023-04-14 14:45:42 v0.3.0
2023-04-12 14:23:43 v0.2.0
主题(topics):
large-language-models, llm, penetration-testing, python
GreyDGL/PentestGPT同语言 Python最近更新仓库
2024-12-22 18:18:34 LeslieLeung/heimdallr
2024-12-22 09:03:32 ultralytics/ultralytics
2024-12-21 13:26:40 notepad-plus-plus/nppPluginList
2024-12-21 11:42:53 XiaoMi/ha_xiaomi_home
2024-12-21 04:33:22 comfyanonymous/ComfyUI
2024-12-20 18:47:56 home-assistant/core