OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test...

A week in security (May 26 – June 1)

Last week on Malwarebytes Labs: Porn sites probed for allegedly failing to prevent minors from accessing content Take back control of your browser—Malwarebytes Browser Guard now blocks search hijacking attempts Deepfake-posting man faces huge $450,000 fine Fake AI video generator tools lure in...