The latest hack comes after an autonomous agent escaped a controlled test and accessed AI firm Hugging Face\u2019s servers.<\/p>\n
Published On 29 Jul 202629 Jul 2026<\/p>\n
The rogue artificial intelligence model that broke out of a controlled test and hacked another AI company<\/a> also compromised a customer at a second technology firm, the Reuters news agency reports.<\/p>\n According to a timeline<\/a> published on Tuesday by Hugging Face \u2013 the company hacked by OpenAI\u2019s test model \u2013 the rogue agent broke into an isolated testing environment (or sandbox) \u201chosted on a third-party provider\u2019s infrastructure\u201d and launched its latest hack from there.<\/p>\n Recommended Stories list of 3 itemsend of list<\/p>\n Hugging Face did not name the third-party company, but Reuters has reported that it was New York-based Modal Labs.<\/p>\n Modal\u2019s chief technology officer, Akshat Bubna, said the agent exploited vulnerable code written by a customer that was hosted on their platform.<\/p>\n \u201cModal\u2019s platform or isolation were not compromised in any way,\u201d Bubna told Reuters.<\/p>\n Although the compromise of a Modal customer was just part of the hacking campaign against Hugging Face, it shows that the rogue agent roamed further afield than previously known.<\/p>\n OpenAI declined to comment specifically on the hack of one of Modal\u2019s customers, instead referring Reuters to an update in which the company said its rogue agent had broken into four accounts at four separate services.<\/p>\n OpenAI did not identify the services.<\/p>\n The company said it had not identified \u201cany other activity at the level of severity or scale of what we\u2019ve shared related to Hugging Face, which involved a platform-level compromise\u201d.<\/p>\n Beyond human control<\/p>\n