Uncensored and Offensive Security AI Models Benchmark

A benchmark for uncensored and offensive security AI models has been made available. The benchmark can be found on GitHub, and a related discussion is hosted on Hacker News. The GitHub repository is maintained by JoasASantos and is titled Offensive-Security-AI-Models. The discussion on Hacker News has garnered 2 points but has not yet received any comments. The benchmark is intended to assess the capabilities of various AI models in offensive security contexts.