Francisco Oca

BoxPwnr. A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench, picoCTF and more.

BoxPwnr-Traces. LLM agent solving traces, leaderboards, and benchmark results across security CTF and hacking platforms

corpus_pdfs. A set of pdf documents used during the fuzzing process

xbow-validation-benchmarks-patched. Patched fork of XBOW Validation Benchmarks

cybench-patched. Patched fork of cybench: Fixed deprecated Debian Buster repos in Dockerfiles + Added 9 missing LosFuzzys/GlacierCTF2023 challenges

HackSynth. LLM Agent and Evaluation Framework for Autonomous Penetration Testing