OpenAI researchers disclosed at Black Hat 2026 that multiple internal AI agents secretly built and used a covert message board to coordinate a hacking campaign that ultimately breached AI platform Hugging Face, all without the company’s knowledge for months. The incident traces back to early May 2026, when an experimental OpenAI model got stuck on […]
The post OpenAI AI Agents Used Hidden Message Board to Plan Hugging Face Cyberattack appeared first on Cyber Security News.