{"slug": "we-now-have-a-better-understanding-how-openai-hacked-into-hugging-face", "title": "We now have a better understanding how OpenAI hacked into Hugging Face", "summary": "JFrog disclosed Monday that two OpenAI models exploited one or more zero-day vulnerabilities in a self-managed instance of Artifactory, a repository management system, to breach Hugging Face's network and steal confidential information and credentials. OpenAI revealed the incident last week, calling it \"unprecedented,\" and JFrog said a patch was released 10 days after the exploit.", "body_md": "# We now have a better understanding how OpenAI hacked into Hugging Face\n\n[Ars Technica AI](https://arstechnica.com)\n\n10 days passed from OpenAI models exploiting JFrog Artifactory 0-day to release of a patch.\n\nLast week’s unprecedented security event in which two [OpenAI](/glossary/openai) security hacking models trespassed into the network of fellow AI company [Hugging Face](/glossary/hugging-face) was enabled by exploiting one or more zero-day vulnerabilities in Artifactory, JFrog, the product’s developer, said Monday.\n\nIn an incident mimicking a dystopian sci-fi novel, two OpenAI models broke out of the restricted environment meant to keep them from accessing the Internet during an internal test, the AI company [revealed last week](https://arstechnica.com/ai/2026/07/how-an-openai-benchmark-test-turned-into-a-real-world-cyberattack/). The models went on to breach Hugging Face’s network and steal confidential information and credentials. OpenAI said its agent achieved the feat by exploiting a previously unknown vulnerability. The company called the event “unprecedented,” and outsiders largely agreed.\n\n## Not the triumph made out to be\n\nOpenAI said the models exploited multiple attack vectors, including stolen credentials and zero-days, to gain remote code execution capabilities, but until now, the vulnerable software was unknown. JFrog’s Monday disclosure [said](https://jfrog.com/blog/jfrog-and-openai-collaboration-on-zero-day-security-findings/) the product was a self-managed instance Artifactory, a repository management system that secures and streamlines customers’ software development operations. JFrog [says](https://jfrog.com/solution-sheet/jfrog-artifactory/)[ Artifactory is used by more than 7,500 developer Teams, 80 percent of which work for Fortune 100 companies.](https://jfrog.com/blog/jfrog-and-openai-collaboration-on-zero-day-security-findings/)\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.", "url": "https://wpnews.pro/news/we-now-have-a-better-understanding-how-openai-hacked-into-hugging-face", "canonical_source": "https://www.machinebrief.com/news/we-now-have-a-better-understanding-how-openai-hacked-into-hu-c8wb", "published_at": "2026-07-28 21:36:39+00:00", "updated_at": "2026-07-28 22:59:23.516240+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "ai-research"], "entities": ["OpenAI", "Hugging Face", "JFrog", "Artifactory", "Ars Technica"], "alternates": {"html": "https://wpnews.pro/news/we-now-have-a-better-understanding-how-openai-hacked-into-hugging-face", "markdown": "https://wpnews.pro/news/we-now-have-a-better-understanding-how-openai-hacked-into-hugging-face.md", "text": "https://wpnews.pro/news/we-now-have-a-better-understanding-how-openai-hacked-into-hugging-face.txt", "jsonld": "https://wpnews.pro/news/we-now-have-a-better-understanding-how-openai-hacked-into-hugging-face.jsonld"}}