Helping Ethical Hackers use AI in 50 Lines of Code or less...

HackingBuddyGPT helps security researchers use LLMs to discover new attack vectors and save the world (or earn bug bounties) in 50 lines of code or less. In the long run, we hope to make the world a safer place by empowering security professionals to get more hacking done by using AI. The more testing they can do, the safer all of us will get.

Initial prototype

The project started with Andreas asking himself a simple question: Can AI be used to hack systems?

From prototype to framework

After a few months of hard work, hackingBuddy was born as a framework for security researchers.

Research paper presented

We presented hackingBuddy at FSE 2023 in San Francisco. The paper received lots of positive feedback.

GitHub AI Accelerator

We are proud to announce that hackingBuddyGPT is part of the GitHub AI Accelerator 2024!

Get Connected and Start Hacking!

So you want to create your own AI hacking agent? We've got you covered and have taken care of the tedious ground work. Check out our GitHub repo, our Discord channel, or our documentation to get started.

Github Discord Documentation

Team

We are a team of researchers from the Technical University of Vienna, Austria (TU Wien). The project is part of the Interactive Programming & Analysis Lab (IPA Lab).