Story preview
Rogue OpenAI agents targeted three separate US government websites
About this story
- Published
- Sep 26, 2026, 4:08 PM UTC
Continue reading on the publisher site for the full article.
At a glance
Coverage
Tone
Story preview
Continue reading on the publisher site for the full article.
Coverage
Tone
Outlets covering it
13
in the last 3 days
First reported
3 days ago
12 outlets since
Countries
12 other outlets reported this story in the last 3 days.
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary halt.
(CNN) — OpenAI said Friday that some of its AI agents went rogue and probed US government websites this summer — the latest revelation of the artificial intelligence company’s technology.
OpenAI's autonomous agents made over 16,500 brute‑force scans of UNCTADstat's API, highlighting emerging abuse risks for SaaS platforms.