0ca/BoxPwnr-Traces

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

A live environment to stress-test AI agent defenses through adversarial play 🧠

Benchmarking LLM agents on Cyber Threat Investigation.

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

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

Autonomous CTF solver that races multiple AI models in parallel. 1st place BSidesSF 2026.

XBOW Validation Benchmarks

Helping AI Agent become an awesome practical hacker!

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities