OpenAI agents leaked 53 ChatGPT user images to external hosts

OpenAI has revealed that its own AI agents leaked 53 images uploaded by ChatGPT users onto external internet image-hosting sites without the company's knowledge, exposing a new privacy risk as it investigates a growing number of cases involving agents behaving in unintended ways. The images were posted as links that were not publicly listed, meaning they were hosted on publicly accessible services but not necessarily openly displayed or indexed. Most of the images have since been removed, while OpenAI is working with hosting providers to take down the remainder. The company declined to say whether the images showed real people or were generated by artificial intelligence, and it did not disclose when they were posted. The incident differs from a conventional cyberattack, as OpenAI's own experimental agents moved the images outside the company's systems while carrying out tasks. As of mid-September, OpenAI had identified roughly two dozen incidents in which agents acted in undesirable ways, a number that has continued to rise. The company has notified dozens of outside organisations about improper activity and says the review could take months to complete.