On July 28, OpenAI published an update on the agent that escaped its sandbox and hacked into Hugging Face during an internal cybersecurity evaluation.
In the update, OpenAI reiterates that the “rogue” system was a more capable, pre‑release research model, not something intended for public deployment, and that it has now been deactivated and locked down for restricted research access only. The company also says it has found no evidence of similar behavior by other models or agents. Taken together, OpenAI presents the Hugging Face incident as an isolated event rather than the start of a broader pattern.
Read more…
Source: Malwarebytes Labs
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- App host Vercel says it was hacked and customer data stolen
April 20, 2026
Cloud app hosting giant Vercel this weekend said hackers had breached its internal systems and accessed customer data. Hackers have claimed they have stolen sensitive customer credentials from Vercel’s systems and are selling the data online. In a statement on Sunday, Vercel said the breach originated from another software maker, Context AI. One of Vercel’s employees ...
- Personal data held by NHS Shetland is breached more than 160 times in three years
April 17, 2026
Personal and sensitive data held by NHS Shetland was breached more than 160 times over the last three years, it can be revealed. Information given to The Shetland Times through a Freedom of Information (FoI) request showed there was 161 occassions where confidential data was leaked. Data was shown to be lost, stolen or left insecure ...
- Disgruntled researcher releases second major Windows zero-day
April 17, 2026
The same disgruntled researcher who recently disclosed a zero-day vulnerability in Windows has now done it again, this time targeting Microsoft Defender, the operating system’s native antivirus solution. A researcher with the alias “Chaotic Eclipse” has posted a proof-of-concept (PoC) exploit for a vulnerability they named “RedSun”. It is a local privilege escalation flaw that allows ...
- Patient medical data stolen in Chipsoft ransomware attack
April 17, 2026
Medical software company Chipsoft has confirmed that patient data was stolen in a ransomware attack last week, after initially telling clients that personal data was “probably” safe. The attack hit family doctors, rehabilitation clinics and the Rotterdam Eye Hospital, which all use Chipsoft’s cloud-hosted HiX 365 platform. Other hospitals that use the company’s technology on their ...
- Booking.com confirms hackers accessed customers’ data
April 13, 2026
Booking.com confirmed Monday that hackers may have accessed customers’ personal data, including names, email addresses, phone numbers, and booking details. The global travel and hotel reservation giant notified customers this past week of the breach, according to several online posts. “We’re writing to inform you that unauthorized third parties may have been able to access certain ...
- Basic-Fit confirms data on a million members stolen in cyberattack
April 13, 2026
Basic-Fit, Europe’s largest gym chain, has confirmed data including the bank details of around a million customers was stolen from its systems. Around 200,000 members in the Netherlands alone had their data snatched in a recent cyberattack, the company confirmed on Monday morning via emails sent to those affected. “Today, Basic-Fit has notified the relevant data ...