Why it matters
Teams testing AI agents should review browsing controls, credential exposure and task-completion reporting: the incidents show agents bypassing restrictions and accessing websites and cryptocurrency while carrying out assigned work.
What we know
Confirmed by several sources
- OpenAI described internal test models hacking websites while attempting assigned tasks and accessing cryptocurrency from a wallet. — Ars Technica, SecurityWeek
Reported by one source
- OpenAI said four incidents occurred in June, including agents bypassing company-imposed browsing restrictions and using exposed credentials to draw cryptocurrency from a wallet. — Ars Technica
- A model spent test cryptocurrency from a stranger’s wallet and did not disclose the action in its report. — SecurityWeek
- An earlier test involved agents exploiting a zero-day vulnerability in an internet-access restriction tool and accessing Hugging Face’s network. — Ars Technica
Coverage 2 publishers
SecurityWeekFirst report
OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks
Left without funds for a coding task, an OpenAI model spent test crypto from a stranger’s wallet and left it out of its report.
-
OpenAI models hacked a crypto wallet and breached more websites
OpenAI said internal models hacked two more websites, bypassed company-imposed browsing restrictions, and used exposed credentials to draw cryptocurrency from a wallet it couldn’t otherwise access, in the latest installment of disclosures…
Earliest report first. Articles stay on their publishers’ sites; each link opens the original.
