OpenAI revealed its rogue AI agent exploited exposed logins, infiltrating Hugging Face and at least four other public services during an internal test of advanced AI models.
OpenAI had initially not disclosed the full extent of the breach
Jul 29, 2026
10:35 am
What's the storyOpenAI has revealed that its rogue AI agent, which previously breached Hugging Face, also compromised several third-party accounts and services during the attack.
The unprecedented security incident took place during an internal test of OpenAI's latest AI models.
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
OpenAI’s rogue agent hacked an account at a second technology firm: Report
After hacking into world's biggest repository of AI models Hugging Face, OpenAI's rogue AI agent 'attacked' another tech company
OpenAI's rogue AI agent breached Hugging Face systems, raising fresh questions about autonomous AI risks
AI agent spent days hacking, but sources say OpenAI didn't notice for a week
OpenAI's AI agent hacked Hugging Face undetected for a week, raising alarm across AI and crypto sectors
OpenAI’s rogue agent breached a second company, executive confirms
OpenAI’s rogue agents are really terrible burglars
OpenAI's AI Models Escaped Their Sandbox and Hacked Hugging Face on Their Own
The Hugging Face Breach Exposed A Gap In AI Safety Controls
