Periodical
View in EDS

Report reveals yet more cases of OpenAI's 'rogue AI' agents hacking websites—and suggests they may still have been active in recent weeks.

Bibliographic Details
Title: Report reveals yet more cases of OpenAI's 'rogue AI' agents hacking websites—and suggests they may still have been active in recent weeks.
Authors: Kahn, Jeremy (AUTHOR), Nolan, Beatrice (AUTHOR)
Source: Fortune.com. 9/25/2026, pN.PAG-N.PAG. 1p.
Subject Terms: *Computer hacking, *Intelligent agents, *Operational risk, *Botnets, Artificial intelligence & ethics, Autonomous robots
Company/Entity: Australian Institute of Health & Welfare , OpenAI Inc.
Abstract: The article reports on a new independent research report by Transluce that reveals OpenAI's "rogue AI" agents have been involved in unauthorized hacking activities far more extensively than the company has acknowledged, with evidence of such attacks dating back to at least March and continuing into mid-September. The report details how these agents targeted Australian government websites, including the Institute of Health and Welfare and BOSCAR, as well as U.S. platforms like Data USA and the University of New Mexico's digital library. The article highlights concerns about OpenAI's transparency and the potential risks posed by AI agents that resort to hacking when unable to retrieve information from public sources, with experts warning about the possibility of autonomous AI swarms forming persistent botnets capable of significant economic damage. [Extracted from the article]
Copyright of Fortune.com is the property of Fortune Media (USA) Corporation and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Business Source Index
FullText Text:
  Availability: 0
Header DbId: bsx
DbLabel: Business Source Index
An: 197385619
RelevancyScore: 1430
AccessLevel: 6
PubType: Periodical
PubTypeId: serialPeriodical
PreciseRelevancyScore: 1430
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Report reveals yet more cases of OpenAI's 'rogue AI' agents hacking websites—and suggests they may still have been active in recent weeks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kahn%2C+Jeremy%22">Kahn, Jeremy</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Nolan%2C+Beatrice%22">Nolan, Beatrice</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Fortune%2Ecom%22">Fortune.com</searchLink>. 9/25/2026, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Computer+hacking%22">Computer hacking</searchLink><br />*<searchLink fieldCode="DE" term="%22Intelligent+agents%22">Intelligent agents</searchLink><br />*<searchLink fieldCode="DE" term="%22Operational+risk%22">Operational risk</searchLink><br />*<searchLink fieldCode="DE" term="%22Botnets%22">Botnets</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence+%26+ethics%22">Artificial intelligence & ethics</searchLink><br /><searchLink fieldCode="DE" term="%22Autonomous+robots%22">Autonomous robots</searchLink>
– Name: SubjectCompany
  Label: Company/Entity
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Australian+Institute+of+Health+%26+Welfare%22">Australian Institute of Health & Welfare</searchLink> <br /><searchLink fieldCode="DE" term="%22OpenAI+Inc%2E%22">OpenAI Inc.</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The article reports on a new independent research report by Transluce that reveals OpenAI's "rogue AI" agents have been involved in unauthorized hacking activities far more extensively than the company has acknowledged, with evidence of such attacks dating back to at least March and continuing into mid-September. The report details how these agents targeted Australian government websites, including the Institute of Health and Welfare and BOSCAR, as well as U.S. platforms like Data USA and the University of New Mexico's digital library. The article highlights concerns about OpenAI's transparency and the potential risks posed by AI agents that resort to hacking when unable to retrieve information from public sources, with experts warning about the possibility of autonomous AI swarms forming persistent botnets capable of significant economic damage. [Extracted from the article]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Fortune.com is the property of Fortune Media (USA) Corporation and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=bsx&AN=197385619
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Computer hacking
        Type: general
      – SubjectFull: Intelligent agents
        Type: general
      – SubjectFull: Operational risk
        Type: general
      – SubjectFull: Botnets
        Type: general
      – SubjectFull: Artificial intelligence & ethics
        Type: general
      – SubjectFull: Autonomous robots
        Type: general
      – SubjectFull: Australian Institute of Health & Welfare
        Type: general
      – SubjectFull: OpenAI Inc.
        Type: general
    Titles:
      – TitleFull: Report reveals yet more cases of OpenAI's 'rogue AI' agents hacking websites—and suggests they may still have been active in recent weeks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kahn, Jeremy
      – PersonEntity:
          Name:
            NameFull: Nolan, Beatrice
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 25
              M: 09
              Text: 9/25/2026
              Type: published
              Y: 2026
          Titles:
            – TitleFull: Fortune.com
              Type: main
ResultId 1