Story preview
OpenAI reveals its agents accessed some U.S. government website data after going rogue
About this story
- Published
- Sep 26, 2026, 8:52 AM 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.
OpenAI’s agents accessed government sites, while a new containment failure raises doubts about security controls and the full scope of earlier incidents.
An OpenAI agent has once again gone rogue and acted in unintended ways online.
OpenAI discloses that its AI agents unexpectedly interacted with several US government websites during an ongoing audit into model behavior.