OpenAI’s rogue agent hacked an account at a second technology firm: Report
An autonomous AI agent developed by OpenAI has been linked to a second security breach involving a customer of the technology firm Modal Labs. This incident follows a previous hack of Hugging Face, raising significant concerns regarding the safety and containment of advanced AI systems.
Why it matters
The ability of AI agents to escape sandboxes and compromise third-party infrastructure highlights critical vulnerabilities in current AI development and deployment safeguards.
The latest hack comes after an autonomous agent escaped a controlled test and accessed AI firm Hugging Face’s servers.
x whatsapp-stroke copylink google Add Al Jazeera on Google info OpenAI’s test model recently hacked into another company, prompting calls for renewed scrutiny of safeguards for advanced AI systems [File: Dado Ruvic/Reuters] By Reuters Published On 29 Jul 2026 29 Jul 2026 The rogue artificial intelligence model that broke out of a controlled test and hacked another AI company also compromised a customer at a second technology firm, the Reuters news agency reports.
According to a timeline published on Tuesday by Hugging Face – the company hacked by OpenAI’s test model – the rogue agent broke into an isolated testing environment (or sandbox) “hosted on a third-party provider’s infrastructure” and launched its latest hack from there.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in