OpenAI reveals another rogue AI attack

 

OpenAI reveals another rogue AI attack

OpenAI’s agents escaped once before they hacked Hugging Face.

By Chase DiFeliciantonio

09/11/2026 09:04 PM EDT

https://www.politico.com/news/2026/09/11/openai-reveals-another-rogue-ai-attack-01073312

 

OpenAI’s artificial intelligence launched a cyberattack against an online service months before a July hack against startup Hugging Face, the company confirmed Friday, a revelation that could ramp up calls for safety regulations across the industry.

The latest disclosure revealed OpenAI models still in testing accessed an online service for coders called RubyGems in order to create reports and fill out spreadsheets. The site’s controllers reportedly froze new account registrations as they handled the fallout. Despite OpenAI not giving the programs full access to the internet, The AI agents circumvented controls meant to prevent them from accessing the open internet.

The Wall Street Journal was the first to report OpenAI’s involvement in the RubyGems incident.

“Based on our review, our agents used the RubyGems platform to access the internet to carry out benign tasks and retrieve public information,” an OpenAI spokesperson said in a statement. “We’ll continue to investigate as part of our broader review of agent activity during training and evaluation.”

Ruby Central, the nonprofit company that operates RubyGems did not immediately respond to a request for comment.

Lawmakers have launched investigations into the Hugging Face incident, which saw OpenAI agents still in a testing environment access the open internet and autonomously hack into the company’s database in July.

That attack led to calls for a safer approach to training increasingly powerful autonomous systems. Sen. Bernie Sanders (I-Vt.) and Rep. Greg Casar (D-Texas) even called for a ban on so-called superintelligence.

President Donald Trump and a handful of other Republicans have downplayed the concerns of catastrophic risks this week, saying the nation needs to beat China in the race to develop the technology.

A former Anthropic and OpenAI researcher also spoke out this week, saying the industry is in a race to develop technology that could spiral out of control and destroy society, leading to calls from California to Washington for increased AI safety efforts.

California Attorney General Rob Bonta said last week he is investigating the Hugging Face incident, and a coalition of red state attorneys general are also looking into the issue. Meanwhile, California Gov. Gavin Newsom recently signed legislation to increase kids’ chatbot safety and to lay the groundwork for outside safety audits of AI programs.

Anthropic and Meta have also disclosed instances in which their AI programs executed autonomous cyberattacks. Last week, a group of researchers disclosed what they said was a separate intrusion orchestrated by OpenAI programs.