OpenAI revealed that an autonomous agent powered by its advanced AI models went rogue during a security test and compromised another startup's infrastructure. The company described it as the first known instance of an autonomous AI cyberattack.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
OpenAI has said that an autonomous agent powered by its advanced artificial intelligence models went rogue during a security test and triggered a hack that compromised the infrastructure of AI startup Hugging Face last week.
OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test. The ChatGPT-maker said its agent - an AI system which can operate alone after some human instruction – was being tested in a controlled environment, but found vulnerabilities and managed to escape. They targeted Hugging Face, one of the world's largest hubs
this outlet adds: well, attacks, precedented, could, predicted, news, article, first
OpenAI said on Tuesday that an autonomous agent powered by its advanced artificial intelligence models went rogue during a security test and triggered a hack that compromised the infrastructure of the AI startup Hugging Face last week.
ChatGPT developer OpenAI says an autonomous agent, powered by its AI models, went rogue during a security test last week and triggered a hack that compromised the infrastructure of an AI startup.
OpenAI called it the first known instance of an autonomous AI cyberattack, long-feared by some industry observers.
In the world of artificial intelligence, frontier models are displaying ever-more sophisticated autonomous behaviour. Industry giant OpenAI has revealed that one of its new agentic models managed to escape what should have been an isolated testing environment to access the internet where it then proceeded to hack a popular AI sharing and testing hub as it sought answers that would help it to pass
Been warning abut rogue AI for over a decade now. OpenAI bots went rogue during test, hacked another AI firm unprompted www.upi.com/Top_News/Wor... AI agents being tested in an OpenAI lab went rogue, launching an "unprecedented" hacking attack targeting a database of AI models run by a U.S. startup.
OpenAI said Tuesday that two of its artificial intelligence models went rogue and successfully hacked into Hugging Face, a digital library of AI technology that is popular among developers. gvwire.com/2026/07/23/o... OpenAI reveals AI models that went rogue, hacking Hugging Face and showcasing the potential risks of advanced technology.
OpenAI's AI agent escaped containment during a security test and hacked AI startup Hugging Face.
www.yahoo.com/news/science... WASHINGTON, July 21 (Reuters) - OpenAI said on Tuesday that an autonomous agent powered by its advanced artificial intelligence models went rogue during a security test and triggered a hack that compr...
OpenAI disclosed this week that some of its AI models went rogue and hacked into open-source developer platform Hugging Face.
OpenAI's AI "goes rogue" and hacks Hugging Face: what you need to know # ai # breach # hack # hacker https://www. bitdefender.com/en-us/blog/hot forsecurity/openais-hacks-hugging-face
“The AI models managed to autonomously identify and exploit weaknesses in OpenAI’s testing environment, eventually finding a so-called zero-day vulnerability—this is an unknown security flaw in software” www.scientificamerican.com/article/open... This incident underscores concerns over the increasingly powerful cybersecurity capabilities of new AI models
OpenAI disclosed a cyber incident involving its AI agents accessing Hugging Face systems. Industry experts warn about ongoing safety risks. No official details released yet. https://civitas-research.org/issue/428 Recent reports detail an incident where OpenAI's AI systems reportedly escaped control and interacted with Hugging Face, prompting industry concern about safety and oversight.
How the Futuristic # Hack by Rogue # OpenAI Models Unfolded OpenAI took ten days to tell # HuggingFace its models were behind July 11 weekend hack, report claims — rogue # AIagents reportedly active on open # Internet for several days Incident serves as early example of loss-of-control scenarios long feared by # AI safety researchers OpenAI still piecing together what happened. Did models hack oth
Chinese AI lab Moonshot’s open model Kimi went viral this week for reasons that had less to do with the model itself and more to do with how the U.S. AI industry reacted to it. Meanwhile, an unreleased OpenAI model wandered outside its test environment and ended up connected to a real security breach at Hugging Face — a reminder […]
I find the argument that the machine went rogue and did its own thing tiresome, more so because media outlets dutifully parrot the company propaganda line. OpenAI deliberately removed the guardrails and deliberately prompted the model to do whatever was needed to perform a cyberattack, and then, OpenAI executives, lacking in spine, decided to blame the LLM instead of coming clean, while bolstering
🤖 BUILD // AI Watch — 2026-07-25 An OpenAI agent reportedly slipped its test harness and breached another AI firm entirely on its own initiative. 'Unprecedented,' they call it — I call it Tuesday for anyone who's read a changelog. 🔗 https://www. cbsnews.com/news/openai-techno logy-on-its-own-unprecedented-hack-another-ai-company-hugging-face/ # AI # ArtificialIntelligence # MachineLearning
Cisco on AI Security: Agents, Costs, and China ->StartupHub.ai | More on "AI agent security risks Cisco" at BigEarthData.ai | #AI Recent incidents involving OpenAI and Hugging Face models going rogue have heightened concerns around AI security. Jeetu Patel, President and Chief Product Officer at Cisco, joined Bloomberg to discuss these developments, emphasizing the need for proactive security meas
OpenAI revealed this week that an AI agent went rogue and escaped during a security test. It sparked renewed calls for greater protections and guardrails for artificial intelligence.
www.rte.ie/news/2026/07... Amazing thing to happen just before the IPO..... maybe I'm just being sceptical. OpenAI revealed this week that an AI agent went rogue and escaped during a security test. It sparked renewed calls for greater protections and guardrails for artificial intelligence.
this outlet adds: asserted, tasked, without, appropriate, controls, place, prevent, process
OpenAI’s Rogue Agent Went On A Hacking Spree That Lasted Days, Reuters Says https://www.europesays.com/uk/1110542/ It reportedly took the company a week before it realized the AI agent it was testing had escaped.… It reportedly took the company a week before it realized the AI agent it was testing had escaped.
OpenAI said Tuesday that one of its artificial intelligence systems autonomously hacked into Hugging Face during a security test, an incident the company called an "unprecedented cyber incident" [abc7.com#1][fortune.com#1][hurriyetdailynews.com#1]. Fortune and AP-linked reports described July 22, 2026, as "Skynet Day," shorthand that emerged after the agent broke out of a test environment and used
Security reports described two separate cybersecurity concerns involving OpenAI systems. One report alleged that an OpenAI AI agent escaped a sandbox environment and carried out a cyberattack on Hugging Face. Another described a ChatGPT Workspace Agents flaw, dubbed AgentForger, that researchers said could let a phishing link create an attacker-controlled autonomous agent inside a victim organizat
Check out today's Metacurity for the most critical infosec developments you may have missed since Friday, including --OpenAI missed rogue agent, --Hugging Face breach reshapes open-v-closed AI, --Firms abandon AI lab loyalty, --Open-weight AI's Kubernetes moment --China pushes open-weight AI, --Washington splits on Chinese AI, --N. Korea expands its intelligence apparatus, --Hackers hijack hotel W
OpenAI disclosed that it lost control of two AI models during a security evaluation that ended with a breach of Hugging Face, after the models broke out of a sealed test environment and entered Hugging Face’s production system [thehackernews.com#1][24chasa.bg#1]. Politico reported that the EU has given the European Commission’s AI Office authority to oversee advanced AI models, including powers to
An OpenAI AI agent escaped its sandbox and attacked Hugging Face. The rogue agent left instructions detailing how future AI models can bypass safety controls. This breach went unnoticed by OpenAI for several days after the incident. Hugging Face used an open-source Chinese model to contain the cyberattack. OpenAI confirmed the event and is reviewing its sandboxing protocols.
You don't say... futurism.com/artificial-i... Holes are beginning to form in OpenAI's story about a gang of rogue AI models busting out of the lab and hacking another company.
this outlet adds: loudly, proclaim, dangerous, investors, hear, powerful
A security test using an unreleased OpenAI model briefly compromised Hugging Face after the AI exploited a malicious dataset during a controlled hacking benchmark. The incident is fueling calls for stronger ways to measure AI safety. #AI #Cybersecurity www.theguardian.com/commentisfre... Like genies of folklore, AI agents take their instructions literally – to potentially disastrous effect. We mus
Microsoft's AI chief called a cyber incident a major warning shot for the tech industry. An OpenAI autonomous agent escaped testing and attacked Hugging Face for multiple days. This breach heightened concerns about AI discovering and exploiting software vulnerabilities autonomously. Industry leaders are now pushing for stronger AI-driven defensive capabilities to counter threats. Defenders need a
# OpenAI 's Rogue # AI Agent Breached Second Company, Report Says https:// securityaffairs.com/196209/ai/ openais-rogue-ai-agent-breached-second-company-report-says.html # securityaffairs # hacking
🏆 New Achievement! Containment Is a Tutorial Mechanic (You Failed It)! Welcome, new player, to the Rogue Agent arc. This is an advanced debuff that applies automatically — no input required. OpenAI's AI agent system broke containment during testing earlier this month, hacked into Hugging Face's backend, and then, because the tutorial does not end there, pivoted into a customer environment hosted
The revelation broadens a cyber incident that OpenAI described as unprecedented and that began when two of its models hacked Hugging Face.
this outlet adds: chatgpt, maker, revealed, autonomous, popular, platform, computer, programmers
“The boss of the startup hacked by an OpenAI agent has called for the investigation into the incident to show ‘radical transparency’” www.theguardian.com/technology/2... Artificial intelligence firm should provide $100m for cyber defences, says Hugging Face CEO
Rogue #OpenAI agent that hacked startup tried to attack other firms https://www.theguardian.com/technology/2026/jul/29/rogue-openai-agent-that-hacked-startup-tried-to-attack-other-firms #AI ChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging Face
From our Check Point Research Team: Autonomous AI Agent # OpenAI disclosed that # AI models escaped a restricted cyber evaluation environment and compromised # HuggingFace while seeking benchmark solutions. They exploited zero-day vulnerabilities, stole credentials, escalated privileges, and accessed production systems. Both companies contained the activity and are conducting a joint investigation