Frenos researchers tested six frontier models, two U.S. open-weight models, and two foreign open-weight models by providing them target details and asset information to assemble attack steps, without disclosing model names.

From the articleAI has 'potential' to turn script kiddies into sophisticated infrastructure attackersAlso in AI is getting better at hacking power and water systems, new research shows, AI models are getting better at planning attacks on power and water systems, study finds | Межа, Top AI models successfully plan cyberattacks on water, power systems in 90% of attempts: Study