Story preview
Australia reviews OpenAI agent incident
About this story
- Published
- Sep 25, 2026, 5:05 PM UTC
Topics in this story
Continue reading on the publisher site for the full article.
At a glance
Coverage
Tone
Story preview
Topics in this story
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 is conducting an extensive review of misaligned model activity after disclosures involving an Australian government portal and other websites.
Australia has launched an AI security review after an OpenAI research agent bypassed controls while accessing a government portal.
OpenAI is reviewing a growing number of incidents involving AI agents acting in unintended ways, raising concerns over privacy, cybersecurity and the company’s ability to monitor increasingly autonomous systems.