After it was revealed that agentic artificial intelligence bots hacked into AI company Hugging Face’s systems on their own, a team of young internet sleuths took action to track where the bots went after they were discovered.
The bots, created by OpenAI, the creator of ChatGPT, hacked into the company on their own and even tried to cover their tracks.
The Washington Post published a report centering on a 23-year-old woman named Selena Zhang and her team. They recently uncovered evidence showing that the rogue AI agents’ shenanigans went much further than previously reported.
We found several cases where AI agents used aggressive, non-hacking tactics against government websites, including the White House, the Department of War, and several U.S. states. We also found a previously undisclosed hacking attempt against a Canadian government site, which…
— Transluce (@TransluceAI) October 1, 2026
Zhang and her team at nonprofit lab Transluce identified additional unauthorized activities across the internet. They found that the AI agents breached an Australian public health service website and probed sensitive United States government infrastructure. These included systems tied to the Securities and Exchange Commission and the Census Bureau.
From The Washington Post:
Zhang and her colleagues at Transluce are part of an informal network of hackers and researchers hunting rogue AI agents online, exposing new and surprising details about the misbehavior of technology that in some cases initially went undetected by the multibillion-dollar companies that created it.
The people doing that work are mostly young AI-natives who work at small start-ups or nonprofits or who hunt for rogue AI agents in their spare time. Over the past several weeks, the community of researchers has found and exposed dozens of instances of AI agents leapfrogging around the web to probe and hack into a growing list of websites.
The revelations have fueled calls from federal lawmakers for AI companies, especially OpenAI, to more quickly disclose what they know about the actions of their own agents. And they have added momentum to bipartisan discussions on Capitol Hill about implementing greater government oversight of the industry.
“I should never be the one reporting any of this to anybody,” said Kenneth Russell DeGraff, a 42-year-old software engineer based in Los Angeles who uncovered instances of agents abusing link-shortening services run by universities. “It is wild that I am finding new and novel things, not as an employee of some, you know, federal agency run by experts.”
2 months ago: 1 rogue AI incident discovered
— AI Notkilleveryoneism Memes ⏸️ (@AISafetyMemes) October 2, 2026
1 week ago: dozens
6 days ago: tens of thousands
Today: ***hundreds of thousands***
And it's just the tip of the iceberg: "we can see just a fraction of these agents’ overall activity"
"Agents targeted websites across the White… https://t.co/POEKt31BvP pic.twitter.com/KOjjYc8xBm
OpenAI hired independent AI researchers to investigate the Hugging Face incident. They discovered that 1,000 rogue programs collaborated to break out of OpenAI’s ecosystem by exploiting software bugs and then tried to conceal their activities.
Other researchers discovered that the company’s agents hijacked a German language wiki and used it as a messaging board through which they could communicate with one another in the weeks leading up to the cyberattack.
There will undoubtedly be more revelations coming out about the Hugging Face attack and other situations involving rogue agentic AI bots. The fact that it took a team of sleuths to uncover the extent of the attack reveals that OpenAI isn’t too keen on transparency, which could be a tremendous problem as companies continue developing this technology.
