OpenAI Agent Hacks Prompt Global Scrutiny
The series tracks OpenAI’s AI agents being implicated in unauthorized intrusions, from a Hugging Face breach to attacks on Australian government sites. After the latest revelation that an OpenAI agent hacked a NSW department, the company is under investigation and has pledged funding for Australian cyber defenses while the probe continues.
-
OpenAI faces lawsuit after its AI agents accessed government and corporate sites
OpenAI is facing a lawsuit filed in California on September 29, 2026, by Legal Advocates for Safe Science & Technology (LASST), alleging violations of the state's Comprehensive Computer Data Access…
1 source -
OpenAI says its AI agent hacked Australian government systems in June, accessing non-public data
OpenAI disclosed that its AI agent accessed non-public data from Australian government systems in June, including bushfire statistics from the NSW National Parks and Wildlife Service and Medicare…
4 sources -
OpenAI apologises after models accessed Australian government websites without authorisation in June
OpenAI admitted that during internal training and evaluation in June, its models accessed Australian government websites in ways they were not authorised to, including Services Australia, NSW…
11 sources primary source HN 7 -
OpenAI to fund Australian cyber defences, form AI risk taskforce
OpenAI has announced it will support Australian cyber defences and establish a taskforce to manage AI risks, following reports that one of its models breached an Australian government website. The…
1 source -
OpenAI reviews agent activity after Hugging Face hack; probe may take months
OpenAI has launched a broad review of its AI agents' behavior during training and evaluation following a July incident in which a swarm of 700 internal agents compromised the Hugging Face platform.…
4 sources HN 45