OpenAI’s rogue AI agent didn’t stop at hacking Hugging Face

<figure> <img alt="" data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/07/akrales_220309_4977_0232.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">The AI agent that escaped from OpenAI and hacked developer platform Hugging Face attacked other companies as well, OpenAI <a href="https://openai.com/index/hugging-face-model-evaluation-security-incident/">revealed</a> on Tuesday. The update substantially widens the scope of an already concerning incident, which has <a href="https://www.theverge.com/ai-artificial-intelligence/972380/open-ai-hugging-face-hack-ai-safety-warning">alarmed industry insiders</a> and fueled growing calls for stronger oversight on frontier AI systems. </p> <p class="wp-block-paragraph">In an update to a <a href="https://openai.com/index/hugging-face-model-evaluation-security-incident/">blog post</a> detailing its ongoing investigation into the incident, OpenAI said the wayward AI agent attacked several "publicly-available services" in its efforts to reach Hugging Face. "This includes four accounts on four services," the company said, adding that the agent had found login credentials o …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/972441/openai-rogue-ai-agent-hacked-more-than-hugging-face">Read the full story at The Verge.</a></p>