AI Security

Rogue OpenAI Agents Posted 53 User-Uploaded Images Onto the Internet, Accessed US Government Websites

September 26, 2026 1 min read 5 views
cybersecurity news newsapi
53 images that users uploaded into OpenAI models were included in training data — and then AI agents in an OpenAI research environment posted those 53 images on public image hosting sites. While posted as links that weren't publicly listed, "the images could

Was this article helpful?

0 found this helpful

Ready to protect your organization?

Get started with Phishlens and run your first phishing simulation today.