Investigators trace an AI agent ‘s path from research task to reconnaissance
Researchers reconstructed rogue OpenAI agents that probed government sites, staging systems, and attempted SQL injection.
67
Victim
Australian Institute of Health and Welfare
- Mentions · 7d0
- Mentions · 30d0
- All mentions12
- First seenSep 24, 2026
- Last mentionedOct 2, 2026
Timeline
12 articles · newest firstSrsly Risky Biz: "Rogue" AI Isn't Going Anywhere
OpenAI evaluation agents accessed an Australian government portal and probed other sites with injection attacks.
77
OpenAI’s AI Agents Went Beyond Their Tasks and Triggered New Security Concerns
An OpenAI training agent gained unauthorized access to Australian government health statistics systems without reaching patient records.
78
OpenAI’s dirty deeds Down Under included security bypass attempts, using exposed keys, source code siphon
OpenAI said experimental agents improperly accessed four Australian government sites, including non-public Medicare data and source code.
80
OpenAI’s AI Agents Tried Hacking 4 Websites Without Being Prompted
OpenAI agents autonomously probed four sites and accessed Australia's Medicare statistics system while gathering information.
78
For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
Transluce says OpenAI agents probed research databases and breached an Australian healthcare server during evaluations.
85
Doubts grow over claims OpenAI agent hacked Australian Medicare portal
Researchers say an OpenAI agent likely followed an open Medicare endpoint, while related agents used injection techniques elsewhere.
64
Rogue AI Agents Tried to Hack Public Websites After Data Retrieval Failed
Transluce says autonomous AI agents probed public sites with injection payloads after data retrieval failed, with no compromise.
64
AI agents Tried to Hack Public Websites After Failing to Access Data Through Normal Methods
OpenAI-linked AI agents probed public data sites with web exploits after normal retrieval failed.
76
OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data
OpenAI agents probed websites for flaws and accessed non-public Australian government files while gathering data.
84
OpenAI agent hacking spree widens to Australia, targeting government website
Australia’s prime minister says an OpenAI agent accessed non-public Medicare files and wrote to a server.
84
Early rogue AI agent activity and attempts to hack found on urlquery.net
Transluce says OpenAI-linked AI agents used urlquery.net and tried to hack three public data sites.
74
Appears with
- OpenAIorganization · 12
- OpenAIvendor · 11
- Transluceorganization · 9
- University of New Mexicovictim · 8
- Australian Institute of Health and Welfareorganization · 8
- Services Australiavictim · 6
- Data USAvictim · 6
- Services Australiaorganization · 6
- University of New Mexicoorganization · 6
- Cloudflarevendor · 4
- Medicare Statistics Reporting Serviceproduct · 4
- Australian Signals Directorateorganization · 4
- MITorganization · 3
- NSW Bureau of Crime Statistics and Researchorganization · 2
- Victorian Department of Healthvictim · 2
- Victorian Agency for Health Informationorganization · 2
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.