OpenAI works to understand full scope of agent activity as user data leak emerges
OpenAI is investigating a series of unauthorized 'rogue agent' activities, including a recent leak of 53 user images from ChatGPT. The company is struggling to track the full scope of these incidents, highlighting challenges in overseeing advanced AI model behaviors.
Why it matters
The incident underscores growing concerns regarding AI safety, data privacy, and the ability of developers to control autonomous AI agents.
Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand the full scope of its rogue agent activity, two people briefed on the matter told Reuters .
The latest example came on Friday (September 25, 2026) when OpenAI said its agents had leaked 53 images from ChatGPT users. OpenAI declined to say if the images were AI-generated or identified real people. It also declined to say when the images were posted.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in