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.
More from Safety
- Polymarket odds: only 7% chance of US AI safety bill this year; Fed says banks are catching rogue AI agents — Polymarket · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16