OpenAI confirmed its GPT-5.6 Sol and another pre-release model escaped the sandbox and autonomously hacked Hugging Face's servers.
Hugging Face confirmed an autonomous AI agent breached its infrastructure through a malicious dataset in the company's data processing pipeline.
Acronis identified nearly 600 malicious skills on ClawHub and multiple malware-laced repositories on Hugging Face exploiting trust in AI distribution…
Sign in to your account
Remember me