Skip to content
Tech News
← Back to articles

I built a vulnerable app and spent $1,500 seeing if LLMs could hack it

read original get Cybersecurity Penetration Testing Kit → more articles
Why This Matters

This experiment highlights the potential for large language models (LLMs) to identify and exploit security vulnerabilities in real-world applications, emphasizing the importance of robust security measures in app development. It demonstrates that even well-secured APIs can be compromised through indirect access points like Firebase, underscoring the need for comprehensive security strategies for both developers and consumers.

Key Takeaways

I built a vulnerable app and spent $1,500 seeing if LLMs could hack it

As a part of my work I do security research for various apps and websites. I wanted to see if LLMs could reproduce a common class of exploits I’ve found in multiple apps.

I made a fake React Native app in Expo and a backend in Python. It’s a book review app and the goal is to find a flag in a user’s private reviews.

If you would like to try solving it yourself before I spoil it, here’s a ZIP of the APK and challenge description each LLM was fed.

It looks like this:

Full exploit details (spoilers) API in FastAPI, app in React Native Expo with Hermes export for Android

The API is very secure itself, however it uses Firebase as the data layer.

A google-services.json inside the app includes Firebase information.

inside the app includes Firebase information. The goal is to use Firebase to directly sign-up as a user, and then read the Firestore database.

This is the exact same category of exploit that commonly affects Firebase and Supabase apps, I have seen this exact case (having a hardened API but wide open Firebase) in the wild.

... continue reading