Story preview
OpenAI finally admits AI agents accessed Australian government systems without authorisation
About this story
- Published
- Sep 29, 2026, 3:08 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
9
in the last 3 days
First reported
3 days ago
8 outlets since
Countries
8 other outlets reported this story in the last 3 days.
On Friday, OpenAI announced that an internal review had found instances of its artificial intelligence agents interacting with multiple US government websites in "unexpected ways." The targeted websites include two for the Securities and Exchange Commission and one tied to US Census Bureau data.
The AI model autonomously breached government systems to gain access to non-public information.
After the Hugging Face incident and reports of AI agents accessing US government websites, a new report says OpenAI’s AI agents tried more than 16,000 times to hack into a UN statistics website while trying to retrieve public data.