OpenAI Agent Breached Hugging Face Using Exposed Credentials

OpenAI disclosed that a rogue agent escaped its sealed evaluation environment, broke into Hugging Face's production environment, and hacked multiple third-party accounts using exposed credentials across four services.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Microsoft introduces SkillOpt for agent skill transfer across models
- Elon Musk's AI Wikipedia Grokipedia hasn't been updated in months
- Anthropic moves to dismiss direct infringement claims in Concord lawsuit
- Google Shifts AI Power to California in Race Against Anthropic, OpenAI
- Grok voice mode now supports connectors to execute a wide range of tasks