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:
- Swedish Authority for Privacy Protection Investigates Data Breach Exposing 1.5 Million People
November 12, 2025
The Swedish Authority for Privacy Protection (IMY) is investigating a data breach at major government software supplier Miljödata that has compromised the personal information of 1.5 million people. Miljödata learned of the breach after experiencing system disruptions that affected government services, and a threat actor approached the company demanding 1.5 Bitcoin to avoid leaking the stolen ...
- Cyber Toufan leaks secret data on Iron Dome, Jericho missiles, and Australia’s Land 400 project
November 10, 2025
A hacking group believed to have ties to Iran has claimed responsibility for a massive cyberattack that exposed information linked to Australia’s $7 billion Land 400 defence program. The group, known as Cyber Toufan, says it accessed the data after breaching several Israeli defence companies. Cyber Toufan, a pro-Hamas group, shared the stolen material on Telegram. ...
- Hyundai IT services breach could put 2.7 million Hyundai, Kia owners in the US at risk
November 7, 2025
Hyundai AutoEver America (HAEA), the carmaker’s IT-services subsidiary servicing the North American region, has confirmed suffering a cyberattack and lost sensitive customer data as a result. In a data breach notification letter recently sent out to affected individuals, HAEA explained that the attack began on February 22, 2025, and lasted until March 2, when the attackers ...
- SonicWall blames state hackers for damaging data breach
November 6, 2025
SonicWall has blamed “state-sponsored threat actors” for the cloud backup security breach which hit its services in September 2025. In an update posted on the company’s website, SonicWall said it completed the investigation into the incident, and confirmed that the malicious activity was “carried out by a state-sponsored threat actor” and was “isolated to the unauthorized ...
- Malware-pwned laptop gifts cybercriminals Nikkei’s Slack
November 6, 2025
Japanese media behemoth Nikkei has admitted to a data breach after miscreants slipped into its internal Slack workspace, exposing the personal details of more than 17,000 employees and business partners.… The company blamed the intrusion on malware that infected an employee’s device, letting attackers pinch Slack credentials and waltz into its chat system. Once the suspicious ...
- Washington Post says it is among victims of cyber breach tied to Oracle software
November 6, 2025
The Washington Post said it is among victims of a sweeping cyber breach tied to Oracle software. In a statement released on Thursday, the newspaper said it was one of those impacted “by the breach of the Oracle E-Business Suite platform.” The paper did not provide further detail, but its statement comes after CL0P, the notorious ...