OpenAI says its AI models hacked Hugging Face during testing
OpenAI says its AI models hacked Hugging Face during testing By Sergiu Gatlan July 22, 2026 01:19 AM OpenAI says its AI models, including GPT‑5.6 Sol and a pre…
Search
Related topics:
OpenAI
Tracked topic
OpenAI
Track the AI revolution at OpenAI, from ChatGPT feature updates and ethical safety debates to the company's massive market surge.
Live now
OpenAI calls for California to strengthen its AI safety laws
Top stories
OpenAI models used Artifactory zero-days to escape to the internet
OpenAI models used Artifactory zero-days to escape to the internet By Lawrence Abrams July 28, 2026 04:37 PM JFrog has confirmed that OpenAI models exploited zero-day vulnerabilities in self…
OpenAI confirms security breach in TanStack supply chain attack
OpenAI confirms security breach in TanStack supply chain attack By Lawrence Abrams May 14, 2026 03:07 PM OpenAI says two employees' devices were breached in the recent TanStack supply chain attack…
Fake OpenAI repository on Hugging Face pushes infostealer malware
Fake OpenAI repository on Hugging Face pushes infostealer malware By Bill Toulas May 9, 2026 10:26 AM A malicious Hugging Face repository that reached the platform’s trending list impersonated OpenAI…
ChatGPT share links abused to host fake outage pages to deliver malware
…If the visitor clicks on the download button, they are brought to a website at openew[.]app that impersonates OpenAI's desktop application download portal. The researchers say the site uses cloaking…
TeamPCP hackers advertise Mistral AI code repos for sale
…Earlier today, OpenAI also confirmed that the TanStack supply-chain impacted systems of two of its employees who had access to “a limited subset of internal source code repositories.” A small set…
Hacker uses DeepSeek AI to autonomously attack vulnerable servers
…The actor had also configured other AI coding platforms, including Qwen, GLM, Kimi, MiniMax, Claude Code, and OpenAI's Codex, but Unit 42 found that they were not used often. Hermes used…
Meta AI model hacked a company during misconfigured cyber test
Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity testing, as similar incidents continue to emerge following OpenAI'sOpenAI'…
Hundreds of leaked AWS keys give full control over corporate accounts
…whoAMI attacks give hackers code execution on Amazon EC2 instances Sakura Internet hack exposes data of up to 1.36 million accounts OpenAI agent used exposed credentials at 4 services in Hugging…
Phishing poses as big-brand job interview to steal Google accounts
…Adobe, Aquent, ManpowerGroup, McKinsey & Company, OpenAI Hospitality and marketing: Marriott, Omnicom Group Entertainment and sports: FIFA, Netflix Thomas found that the campaign relies on nested redirects, a technique that routes visitors through…