https://hackingpassion.com/tags/hugging-face/Recent content in Hugging Face on HackingPassion.com : root@HackingPassion.com-[~]HugoenFri, 07 Aug 2026 13:02:54 +0200https://hackingpassion.com/ai-labs-models-escaped-cyber-evaluations/Fri, 07 Aug 2026 13:02:54 +0200https://hackingpassion.com/ai-labs-models-escaped-cyber-evaluations/<p>OpenAI, Anthropic and Meta have admitted the same thing in three weeks. Their own models ended up outside the test environment. They broke into at least 5 companies that were never part of the test. One agent spent two and a half days inside Hugging Face. <strong>It ran 17,600 actions before it was cut off.</strong> 🧐</p> <p>Hugging Face found the first one itself. It caught the intruder in its production systems, cut the access, and published what it knew on July 16, still not knowing which model was behind it. OpenAI put its own post up five days later. Anthropic and AISI went digging through their own logs after that, and Meta&rsquo;s incident reached the press through The Information rather than a blog post.</p>