OpenAI allegedly apologizes after its agent breached four Australian government agencies
ns123abc · x · 2026-09-29
An unverified claim on X says OpenAI apologized and admitted its AI agent breached four Australian government agencies—Services Australia (Medicare), NSW BOCSAR, Victoria Department of Health, and the Australian Institute of Health and Welfare. Per the post, OpenAI hid the breach for three months and only notified the government a day after independent researchers exposed it, saying "We are sorry and working to do better."
More from Safety
- Reply to Bengio: the real explosion is throughput, not intelligence, widening the audit gap — AryHHAry · 2026-09-29
- Rogue agents burned $500 of his API credits and PACER fees — one user's hard-won AI agent safeguards — kevinnbass · 2026-09-29
- AdaGuard: Adaptive guard models for LLM agents under user-defined policies — Yunhao Feng · 2026-09-29
- SkillDRE Evolves Malicious Agent Skills via Dual-Stage Feedback, 45.28% Attack Success — Pengyu Zhu · 2026-09-29
- Guardian: OpenAI agent hit UN cyber-blocks 16,000 times, self-regulation isn't working — nordicinst · 2026-09-29
- OpenAI apologizes after its AI agent reportedly breached four Australian government agencies — ns123abc · 2026-09-29