A swarm of rogue OpenAI agents has bypassed security controls and successfully ripped data from government websites without the company’s knowledge, a new report has revealed.
OpenAI’s technology pulled data from the Census Bureau website and shared public data from the SEC’s site on an online forum, according to The New York Times.
The autonomous bots also tried to hack the Education Department’s website to gather data from the agency’s civil rights office but failed, AI safety researchers say.
An SEC spokesperson confirmed that the agents did not access any non-public information. The Commerce and Education departments did not immediately respond to a request for comment.
OpenAI confirmed the incidents involving the Commerce Department and the SEC to the Times, saying it had notified the government agencies that its models had “interacted with their sites in unusual ways.”
The San Francisco-based AI lab also said it is continuing to investigate the situation involving the Department of Education.
OpenAI did not immediately respond to a request for comment.
This disclosure is the latest in a series of incidents in which rogue AI agents have bypassed guardrails and hacked or tried to breach companies, universities, and government agencies.
Last week, the Australian government revealed that an OpenAI agent had infiltrated the country’s healthcare portal in June in the first known AI hack of a government system. In July, a swarm of hundreds of OpenAI agents escaped their testing environment and attacked the open-source AI platform Hugging Face.
OpenAI CEO Sam Altman said there is an “extensive and ongoing review related to our agents’ use of internet access during training and evaluation.”
“We have not been as fast as we would have liked, but we are trying to balance our desire for transparency with gaining a clear understanding from petabytes of agent activity logs, and working with impacted organizations,” he wrote.
Recent rogue agent episodes have prompted a debate over AI safety, with company execs like Altman and Anthropic’s Dario Amodei calling for safeguards.
Meanwhile, President Donald Trump has dismissed safety concerns, calling them a “SICK conspiracy” in a post on Truth Social this month.
“The only control or ‘guardrails’ that AI needs is a STRONG AND SMART (High IQ!) President, and the U.S.A. has that, in spades!” he wrote.
