NiceTryGPT: Less pattern matching. More actual hacking.

A developer released NiceTryGPT, an open-source project that helps CTF (capture-the-flag) authors reduce the effectiveness of cheap LLM shortcuts by removing obvious patterns from challenges while preserving their original vulnerabilities and learning objectives. The tool currently covers examples such as IDOR, path traversal, and SQL injection, aiming to make challenges less about pattern matching and more about genuine hacking rather than making them fully "AI-proof.

I built NiceTryGPT, an open-source project for CTF authors who want to make cheap LLM shortcuts less effective without making challenges harder or more annoying for humans. The idea is simple: «Increase uncertainty, not complexity.» NiceTryGPT keeps the same vulnerability and learning objective, but removes obvious patterns that can turn a challenge into a one-shot LLM answer. Current examples include IDOR, path traversal and SQL injection. I'm not trying to make CTFs “AI-proof” — just a little less about pattern matching and a little more about actual hacking. 😄 GitHub: https://github.com/aleff-github/NiceTryGPT https://github.com/aleff-github/NiceTryGPT Project page: https://aleff-github.github.io/NiceTryGPT/ https://aleff-github.github.io/NiceTryGPT/ Feedback from CTF players and authors is very welcome. showdev cybersecurity ai opensource