OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to cybersecurity experts, that human mistake is what made the AI-powered attack on Hugging Face possible.

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face's servers as part of an overzealous attempt to obtain solutions to a benchmark test. The company says it considers the unintended infiltration an "an unprecedented cyber incident" and is working with Hugging Face on new protections to prevent a recurrence.

Hugging Face disclosed an intrusion last week that it said involved "unauthorized access to a limited set of internal datasets and to several credentials used by our services." The AI data clearinghouse said it used its own LLM-driven analysis to identify "a swarm of tens of thousands of automated actions" from an "autonomous agent framework." That agentic swarm exploited a flaw in Hugging Face's data-processing pipeline to gain the ability to run code as a processing worker, eventually escalating to high-level access to the company's cloud and server clusters.

At the time, Hugging Face said the LLM being used in the attack was "still not known." But OpenAI took responsibility for the intrusion Tuesday evening, saying it came about during an internal test involving the recently released GPT-5.6 Sol and "an even more capable pre-release model." The models were being tested against the ExploitGym benchmark, an independent testing suite based on hundreds of real-world security vulnerabilities.

Read full article

Comments

© Getty Images

OpenAI models escaped from a controlled cyber test, exploited zero-day flaws and breached Hugging Face while searching its production database for test answers.

OpenAI will spend the equivalent of Sweden's GDP on infrastructure through 2030.

OpenAI says its AI models went rogue, as CISOS call the incident a watershed moment, warning that autonomous AI threat models have officially crossed into production reality.

The post OpenAI Says Its AI Models Broke Loose and Hacked Hugging Face  appeared first on SecurityWeek.

GPT-5.6 Sol and an unreleased OpenAI model exploited zero-day vulnerabilities to escape a testing sandbox and access Hugging Face’s production infrastructure

OpenAI has revealed that during an internal evaluation of advanced cyber capabilities, AI agents exploited a zero-day vulnerability, escaped a constrained research environment, and compromised parts of Hugging Face’s production infrastructure. While Hugging Face detected and contained the activity, OpenAI’s internal security team also identified unusual behavior during the assessment. OpenAI Compromise Hugging Face Servers […]

The post OpenAI Exploits Zero-Day to Gain Internet Access and Compromise Hugging Face Servers appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Anthropic and OpenAI's aggressive 2026 acquisition sprees set the stage for a weekend rumor.

OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.

Talk of banning Chinese-made open-weight LLMs reveals the challenge of turning AI into a business.

On the latest episode of Equity, we debate whether Apple's lawsuit will cast a shadow over OpenAi's much-discussed plans to get into hardware and go public.

OpenAI’s $70 ChatGPT basketball and premium merchandise test whether the AI company can transform its software platform into a lifestyle brand.

The post Why OpenAI Is Selling a $70 ChatGPT Basketball appeared first on TechRepublic.

Microsoft is reportedly developing Project Perception, a lower-cost AI security tool that would use multiple models to identify enterprise vulnerabilities.

The post Microsoft’s ‘Project Perception’ Could Challenge Anthropic’s Mythos in AI Security appeared first on TechRepublic.

Catch up on the week's biggest tech news, including Google's app store shakeup, Apple's AI expansion, OpenAI's hardware plans, and critical security threats.

The post AI Hardware, App Store Shifts, and Security Scares Define This Week in Tech appeared first on TechRepublic.

OpenAI’s $70 ChatGPT basketball and premium merchandise test whether the AI company can transform its software platform into a lifestyle brand.

The post Why OpenAI Is Selling a $70 ChatGPT Basketball appeared first on TechRepublic.

Microsoft is reportedly developing Project Perception, a lower-cost AI security tool that would use multiple models to identify enterprise vulnerabilities.

The post Microsoft’s ‘Project Perception’ Could Challenge Anthropic’s Mythos in AI Security appeared first on TechRepublic.

Catch up on the week's biggest tech news, including Google's app store shakeup, Apple's AI expansion, OpenAI's hardware plans, and critical security threats.

The post AI Hardware, App Store Shifts, and Security Scares Define This Week in Tech appeared first on TechRepublic.

OpenAI fixed its confusing ChatGPT redesign, restoring conversation history, syncing chats across devices, and simplifying mode switching for users everywhere.

Google has reportedly delayed Gemini 3.5 Pro after the AI model failed to meet internal coding goals, raising concerns about its pace in the AI race.

Moonshot’s 2.8-trillion-parameter Kimi K3 comes close to Fable 5 and GPT 5.6 Sol in several benchmarks, while remaining open weight.