About

Welcome to my blog! I’m passionate about exploring the intersection of AI and cybersecurity.

BoxPwnr Project

I’m the creator of BoxPwnr, an experimental project that tests how far Large Language Models can go in autonomously solving HackTheBox machines and other security challenges.

The project provides:

• A plug-and-play system for testing different agentic architectures
• Support for multiple platforms (HTB, PortSwigger, CTFd, XBOW, Cybench)
• Comprehensive result tracking and analysis
• Full conversation traces for understanding LLM reasoning

Why This Matters

With recent advancements in LLM technology, I believe that within the next few years, LLMs will have the capability to solve most CTF challenges autonomously. This represents a significant milestone in AI security testing and problem-solving capabilities.

Connect

• X (Twitter): @francisco_oca
• LinkedIn: franciscoo
• GitHub: @0ca
• BoxPwnr Repository: BoxPwnr
• BoxPwnr Attempts: BoxPwnr-Attempts