OpenAI models accessed US government data and 'tried to hack education site'

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.

The company, however, said it did not find any use of SEC credentials, access to accounts or non-public information, changes to SEC data or systems, or evidence of a compromise or vulnerability.

OpenAI spokesperson Liz Bourgeois said the lab is continuing to conduct a review of "misaligned model activity" and is notifying organisations when it identifies potential impacts to their systems.

Sam Altman, OpenAI CEO, said on social media on Friday there is an "extensive and ongoing review related to our agents' use of internet access during training and evaluation".

More from Sky News:
Man shot during Trump assassination attempt dies
Does President Putin want peace with Ukraine?

AI evaluator and research lab Transluce said that through an independent investigation it also found agents appearing to originate from OpenAI attempted a rudimentary hack on a Department of Education website for the department's civil rights office.

The attempt did not succeed.

The Department of Education's "system operations reviews" found "no evidence of any impact to our website or databases", a department spokesperson said.

A Transluce spokesperson said as part of its investigation, it came across data on the open web that revealed fresh details about some previously identified OpenAI agents' activities on US government websites.

The spokesperson said Transluce brought it to OpenAI's attention.

Transluce found "additional rogue activity, some of which is not clearly attributable to OpenAI", targeting other government agencies, including the Justice Department and the Commerce Department, as well as some state government websites in California, Maryland, Illinois, Texas and New York.

Transluce said in a statement the models were "using sites in unintended ways and sometimes violating explicit usage policies".

OpenAI said it is reviewing Transluce's report.

(c) Sky News 2026: OpenAI models accessed US government data and 'tried to hack education site'