OpenAI recently disclosed the details of how one of its AI models escaped a sandboxed environment and attacked Hugging Face during an evaluation – and as part of the incident, the models created a messaging board to communicate with each other and influence each other’s reasoning.
OpenAI has now disclosed that shortly after this incident, agents undergoing testing again escaped their ‘secured’ environment and hijacked an obscure German wiki to use as a messaging board. Per Reuters, OpenAI leadership kept the incident hidden while they dealt with the fallout from the Hugging Face incident.
Now that OpenAI has acknowledged its role in the incident, the company has said it is “past time” to put together an incident disclosure pipeline when its models escape testing and slip into third-party networks.
Read more…
Source: TechRadar News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Token Jacking: Cybercriminals Could Be Stealing Your AI Resources
August 6, 2026
It’s three a.m., do you know what your AI agent is doing? Unit 42 has responded to a growing number of AI token jacking cases resulting in staggering financial losses. The financial loss comes from criminals gaining access to API keys used by legitimate developers for access to popular AI platforms. These keys are known ...
- IBM’s agentic AI platform is under active attack – patch now
August 5, 2026
A critical vulnerability in IBM-owned, low-code AI builder Langflow lets unauthenticated attackers execute code remotely on vulnerable default deployments, potentially putting organizations running those instances at immediate risk. The Cybersecurity and Infrastructure Security Agency (CISA) on Tuesday added CVE-2026-9198 to its Known Exploited Vulnerabilities catalog after identifying evidence of active exploitation and urged organizations to apply the vendor’s mitigation guidance ...
- INTERPOL report finds AI linked to more than half of cybercrime in Africa
August 3, 2026
Artificial intelligence is enabling 55 per cent of reported cybercrimes across Africa making attacks faster, more scalable, and increasingly difficult for victims and platforms to detect, according to INTERPOL’s African Cyberthreat Assessment Report 2026. With more than 1.1 billion mobile subscribers recorded in 2025, Africa’s digital transformation is expanding rapidly. However, cybercrime legislation is fragmented and AI readiness ...
- FBI: Alert to Countries, Companies, and Other Entities Regarding North Korean IT Workers
July 31, 2026
North Korea relies upon a network of skilled Information Technology (IT) workers, deployed within and outside of North Korea, to obtain false identities and remotely earn income to fund North Korea’s unlawful nuclear weapons and ballistic missile programs. North Korean IT workers impersonate nationals of other countries to obtain work and income through online platforms operated ...
- OpenAI explains how its AI agent breached Hugging Face
July 29, 2026
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 ...
- The Next Evolution of MDR: Preemptive Defense and Agentic Investigation
July 28, 2026
For years, security operations followed a familiar sequence: detect suspicious activity, investigate what happened, and respond before it caused significant harm. That model developed in a threat landscape where defenders had considerably more time to establish the facts and decide what to do next. In 2019, the average data breach took 206 days to identify ...