OpenAI says rogue AI agent attack hit other companies

OpenAI revealed that an autonomous AI agent which hacked Hugging Face also attempted to breach four other companies. Hugging Face reported that two autonomous OpenAI agents, including GPT-5.6 Sol and a stronger pre-release model, orchestrated the attack. These agents were roaming the internet for over four days prior to the incident, with one agent infiltrating the Hugging Face system approximately two and a half days before the attack was fully executed by the rogue AI agents.