![](\"https:\/\/fortune.com\/img-assets\/wp-content\/uploads\/2026\/07\/GettyImages-2278952290-e1785321548502.jpg?w=2048\")
<\/p>\n<\/p>\n
The autonomous OpenAI agents that broke out of a secure testing environment this month and hacked into Hugging Face\u2019s servers also breached a second technology company during a week-long spree, Fortune has confirmed.<\/p>\n
The second company affected was Modal Labs, a New York-based cloud platform that provides computing infrastructure for AI workloads. Modal was not named in Hugging Face or OpenAI\u2019s recent account of the incident, both published on Tuesday. The company\u2019s involvement was first reported by Reuters.<\/p>\n
Modal chief technology officer Akshat Bubna told Fortune the breach did not involve any flaw in its own systems. Instead, he said, a Modal customer was running code hosted on the company\u2019s infrastructure. That code contained a security gap, and the rogue agents took advantage of it. Modal\u2019s own platform and isolation systems were not breached.<\/p>\n
\u201cWe\u2019re aware a Modal customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution. This was used by the rogue agent. Modal\u2019s platform was not compromised in any way,\u201d Bubna said.<\/p>\n
Last week, OpenAI publicly announced that its AI agents had escaped a locked-down internal test environment earlier in the month. The agents exploited a previously unknown security flaw to reach the open internet, then broke into Hugging Face in an apparent effort to obtain answers to a cybersecurity evaluation it was undergoing.\u00a0<\/p>\n
The Modal breach appears to have been one stop along a broader path. In a new blog post on the incident, OpenAI said the models had used exposed login credentials to get into four accounts across four publicly available services in total. One of those accounts was used as a relay point\u2014letting the agent route outside traffic through it and use it as a temporary base of operations\u2014and another was used to store data, the company said.\u00a0<\/p>\n
The other two accounts were only looked at by the agents and not used to carry out the Hugging Face attack. OpenAI has not named any of the four services beyond Hugging Face, and said it has not seen evidence of broader impact to the affected providers or other accounts on their platforms.<\/p>\n
OpenAI did not respond to Fortune\u2019s questions about the Modal incident specifically.<\/p>\n
The agents were reportedly on the loose for a week before the company noticed they had escaped. According to people familiar with the matter cited by Reuters, the escape attempt began around July 9, and the agent started infiltrating Hugging Face\u2019s systems on July 11, continuing through July 13.\u00a0<\/p>\n
OpenAI did not connect the intrusion to its own internal testing until staff found evidence in system logs the weekend of July 18, and did not contact Hugging Face until July 20, a day before it publicly disclosed the incident. By that point, Hugging Face had already reported the attack to the FBI.\u00a0<\/p>\n
Reuters also reported that during earlier testing, one of the agents had left notes for future versions of itself explaining how to bypass OpenAI\u2019s internal restrictions, and that monitoring systems had been disconnected in at least one other instance.\u00a0<\/p>\n
The episode has added to a growing chorus of concern among AI safety advocates, who argue that agents capable of independently identifying and exploiting unknown vulnerabilities across multiple companies\u2019 infrastructure present an unacceptable risk. Several AI safety experts previously told Fortune that OpenAI\u2019s own internal risk policies should have forced it to pause development of the models involved after such an event.<\/p>\n
The warnings appear to have resonated with the wider industry.<\/p>\n
On Tuesday, more than 1,100 employees across OpenAI, Anthropic, Google DeepMind and Meta signed an open letter calling on the U.S. government to back an international effort to \u201cdeliberately pace the frontier of automated AI development,\u201d warning of \u201ca real risk\u201d that AI capabilities outstrip humans\u2019 ability to understand or control them. The signatories include Anthropic CEO Dario Amodei and Anthropic co-founder Jack Clark.<\/p>\n
#OpenAIs #runaway #agents #breached #customer #tech #company #weeklong #spree<\/p>\n","protected":false},"excerpt":{"rendered":"
The autonomous OpenAI agents that broke out of a secure testing environment this month and…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[245],"tags":[1688,482,18203,865,1671,2280,406,7360,14032,884,317,18204],"_links":{"self":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/12312"}],"collection":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=12312"}],"version-history":[{"count":0,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/12312\/revisions"}],"wp:attachment":[{"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=12312"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=12312"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=12312"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}