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:
- Healthcare giant Abbott probes two cyber incidents amid extortion claims
July 20, 2026
Abbott Laboratories, one of the world’s largest healthcare and medical device companies, is investigating two apparently unrelated cyber incidents after confirming unauthorized access to internal systems. While Abbott says there has been no impact on manufacturing, laboratory operations, or patient care, cybercriminal groups ShinyHunters and ShadowByt3$ claim the breaches were far more extensive. Those claims ...
- Tech support scam caused massive data breach at Australian airline Qantas
July 16, 2026
Australia’s Privacy Commissioner has revealed a tech support scam was the cause of the massive 2025 data breach at Australian airline Qantas and found the carrier didn’t breach its privacy obligations despite leaking personally identifiable information for 5.7 million customers. The Commissioner reached that conclusion, and a decision not to open a formal privacy probe, in ...
- Supermarket chain Lidl warns customers after data leak
July 10, 2026
Unknown individuals managed to gain access to customer data held by the supermarket chain Lidl. The German company informed affected customers of this via email this week. Thus far, the supermarket chain has declined to say how many customers were affected. However, the discount retailer did state that it has notified the Dutch Data Protection Authority. Read ...
- Accenture confirms breach after hacker steals 35GB of source code and other data
July 9, 2026
Accenture has confirmed suffering a cyberattack, days after threat actors started selling an archive allegedly coming from the firm. “We are aware of this isolated matter, and we have remediated its source. There is no impact to Accenture operations and service delivery,” Accenture said in a statement. It follows a relatively unknown threat actor called 888 posting ...
- An unnamed US county paid $1M extortion demand to cybercriminals
July 9, 2026
A US county reportedly paid $1 million to Kairos, an extortion gang that claimed to have stolen more than 2 TB of data, but the county never received independently verifiable proof that the stolen files had been deleted – just the criminals’ promise. This means the county’s stolen files may turn up for sale on a ...
- 6.9 million driver’s license numbers stolen from AssuranceAmerica
July 9, 2026
Insurance provider AssuranceAmerica has confirmed a data breach affecting the personal information and driver’s license numbers of up to 6.9 million people. AssuranceAmerica provides car and rental insurance to customers across 14 US states through a network of over 9,500 independent agents. The breach notice letter also mentions information about customers’ auto insurance policies and accounts, their drivers and ...