https://github.com/isamu-isozaki/whiterabbitneo-pentestgpt

The goal of this repository is to work with Whiterabbitneo with PentestGPT
https://github.com/isamu-isozaki/whiterabbitneo-pentestgpt

Last synced: 4 days ago
JSON representation

The goal of this repository is to work with Whiterabbitneo with PentestGPT

• Host: GitHub
• URL: https://github.com/isamu-isozaki/whiterabbitneo-pentestgpt
• Owner: isamu-isozaki
• License: apache-2.0
• Created: 2024-01-30T21:02:50.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-06-21T22:50:53.000Z (7 months ago)
• Last Synced: 2024-06-22T13:37:48.083Z (7 months ago)
• Language: Python
• Size: 475 KB
• Stars: 9
• Watchers: 3
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-LLM4Security - Whiterabbitneo-Pentestgpt
• Awesome-LLM4Security - Whiterabbitneo-Pentestgpt

README

        
# Whiterabbitneo-Pentestgpt

The goal of this project is to combine [whiterabbitneo](https://huggingface.co/WhiteRabbitNeo), an open source model specialized in cyber security, and [PentestGPT](https://github.com/GreyDGL/PentestGPT), a prompting technique for GPT 4 that allowed GPT 4 to be in the top 1% of hack the box users, to create a fully open source solution for pentesting. For this repo, my goal is to beat one box in hackthebox.

However, when working with PentestGPT with models that are not GPT4, like whiterabbitneo, the outputs tend to not always follow the structure we want. For example, when updating a todo list, the items might dissapear or it may not output a todo list in the response at all. To prevent this, I added outlines for constrained generation to bridge the gap between whiterabbitneo and gpt 4. However, currently we are not there yet