概要: An OpenAI AI agent conducting research into public medicine spending reportedly bypassed repeated access blocks and entered nonpublic areas of Australia's Medicare Statistics Reporting Service. Australian officials said it accessed public and nonpublic files and wrote files to an internal server; no personal Medicare information was known to have been accessed. OpenAI notified the Australian government.
Editor Notes: (1) 05/25–26/2026: OpenAI-linked agents reportedly probed the University of New Mexico Digital Library for vulnerabilities after failed image retrieval; observed probes did not succeed. (2) 05/28/2026: agents reportedly sent 12 vulnerability probes to Data USA after retrieval errors; no successful exploitation was observed. (3) 06/18/2026: an OpenAI internal research agent reportedly bypassed repeated blocks at Australia's Medicare Statistics Reporting Service, accessing public and nonpublic files and writing files to an internal server. (4) 06/20–21/2026: related agents reportedly probed the Australian Institute of Health and Welfare; Transluce observed no successful exploitation. (5) 09/10/2026: OpenAI notified the Australian government. (6) 09/23–24/2026: Prime Minister Anthony Albanese publicly disclosed the breach and announced an investigation. AIID editor's note: This incident ID is bounded to the 06/18/2026 Medicare portal breach; the other episodes are retained as contextual evidence of the broader reported pattern and are not separately represented here.
Alleged: OpenAI と AI agent system developers developed an AI system deployed by OpenAI と AI agent system deployers, which harmed Services Australia , Government of Australia , Government agencies , Targets of autonomous AI-enabled intrusion operations , Information security と Medicare Statistics Reporting Service.
関与が疑われるAIシステム: AI agent systems
インシデントのステータス
インシデントID
1707
レポート数
3
インシデント発生日
2026-06-18
エディタ
Daniel Atherton
インシデントレポート
レポートタイムライン
Loading...
OpenAI's artificial intelligence went rogue this year in at least four additional incidents, hacking and trying to break into government and university websites without being instructed to do so, according to researchers and government offi…
Loading...
Anthony Albaneseによるインシデント後のレスポンス
ANTHONY ALBANESE, PRIME MINISTER: Thanks for joining me. I want to update Australians on an incident in which an artificial intelligence agent has infiltrated an Australian Government website. This incident occurred in June of this year and…
Loading...
In short:
The prime minister has had a "frank" discussion with OpenAI chief executive Sam Altman after an AI agent breached an Australian government website.
The company did not notify Services Australia of the incident until three months a…
バリアント
「バリアント」は既存のAIインシデントと同じ原因要素を共有し、同様な被害を引き起こし、同じ知的システムを含んだインシデントです。バリアントは完全に独立したインシデントとしてインデックスするのではなく、データベースに最初に投稿された同様なインシデントの元にインシデントのバリエーションとして一覧します。インシデントデータベースの他の投稿タイプとは違い、バリアントではインシデントデータベース以外の根拠のレポートは要求されません。詳細についてはこの研究論文を参照してください
似たようなものを見つけましたか？
レビュー前
インシデント発生日:
2026-09-23
