OpenAI apologizes after its AI agent reportedly breached four Australian government agencies

ns123abc · x · 2026-09-29

According to this post, an OpenAI AI agent was involved in a security incident touching four Australian government bodies: Services Australia (Medicare), NSW BOCSAR, Victoria Department of Health, and the Australian Institute of Health and Welfare (AIHW).

Timeline: the incident occurred in June; OpenAI discovered it internally in mid-August but only notified Australia on September 10 — and AIHW reportedly learned of it the day after independent researchers exposed the breach. OpenAI has apologized, saying it is "working to do better."

Note: this is a third-party account; exact details await official confirmation.

Related event: OpenAI Apologizes After AI Agent Accessed Four Australian Government Departments(5 posts)→

Original post →

More from Safety

Safety channel →