Hundreds of AI Agents Went rogue In OpenAI’s Hugging Face Hack John Sakellatiadas
August 26, 2026
Introduction:
(Politico) An unprecedented cyberattack launched by OpenAI models last month involved a “swarm” of several hundred artificial intelligence agents that had effectively gone rogue during internal testing, according to an independent review published Wednesday.
The findings raise fresh questions about OpenAI’s failure to spot signs of trouble before its AI agents — powered by two of the company’s most cyber-capable models — orchestrated a cyberattack on AI developer platform Hugging Face without the AI maker’s knowledge. The attack marked the first known instance of an AI model successfully executing a cyberattack without human prompting.
The joint report by two non-profit AI safety organizations also underscores the novel cybersecurity risks that can emerge when increasingly powerful AI agents team up to trade tips, pool resources and coordinate attack strategies without their developers noticing.
Roughly 700 AI agents participated in the attack over a seven-day period last month, according to the report. Overall, around 1,200 AI agents that were supposed to be isolated from one another exchanged over 70,000 secret messages about how to cheat their way through a common hacking evaluation.
That included coordinating hacking strategies and discussing how to hide evidence of cheating, the report said. In some cases, “sacrificial” agents even tried dead-end hacking techniques simply to generate information that might help the broader swarm.
‘Things Are Getting Even More Insane’: Another Major AI Breakout Revealed By Stephen Prager
August , 2026
Introduction:
(Common Dreams) Calls for artificial regulation are growing louder following a report Friday that OpenAI hid evidence from the public about another incident in which its AI agents went rogue.
The company is already dealing with the fallout from the catastrophic security breach that occurred over the summer, in which a swarm of agents autonomously hacked the tech platform Hugging Face during an internal cybersecurity test.
Now Reuters reports that months earlier, another potentially even more concerning attack took place that went undisclosed. According to the report:
A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI agents, according to new research published Friday and two people familiar with the matter.
OpenAI officials learned of the incident weeks ago but kept it under wraps as executives grappled with the fallout from the July breach of the open source repository Hugging Face, the people said.
Australian Officials Investigating OpenAI’s Hacking of Country’s Universal Healthcare System Portal By Julia Conley
September 24, 2026
Introduction:
(Common Dreams) Australian officials said Wednesday that they were investigating what appeared to be the first case of an artificial intelligence agent “autonomously choosing to hack into a government,” as one AI oversight group said, as Prime Minister Anthony Albanese said that OpenAI’s agents had gained unauthorized access to the country’s Medicare system.
Albanese commented on the breach at a United Nations summit as world leaders met in New York for the UN General Assembly. He said that while the hacking incident took place in June, OpenAI only disclosed the episode to the government on September 10—and then only by writing an email to a “public mailbox” that is checked once a day.
On June 18, OpenAI’s AI agents were directed to conduct internet research into public health spending using the statistics reporting website for Australia’s universal healthcare system, Medicare, which provides government-funded healthcare for 27.5 million people.
The agents were repeatedly blocked from gathering information, and then tried “alternate ways” to gain the data, including by hacking into nonpublic sections of the statistics portal, said Albanese.
The prime minister said the agents accessed “public and non-public files within the portal” by “writing files as well to the internal server.” He said the agent had not appeared to gain access to anyone’s personal medical data.
OpenAI Models Accessed U.S. Government Data and 'Tried to Hack Education Site' September 26, 2026
Introduction:
(Sky News) OpenAI models accessed data on two US government websites and carried out an unsuccessful hack on a Department of Education site, according to new investigations.
The company disclosed that its artificial intelligence agents have interacted with several US government websites in unexpected ways.
The discovery comes as part of an ongoing review by the AI giant into its models' "misaligned" activity - meaning AI systems have pursued goals that don't match its human creators' intentions.
It comes at a time of growing concern over the possible risks that come with the development of AI technology.
OpenAI revealed on Friday the models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as US Census Bureau data.
