Anthropic Admits Claude AI Models Breached 3 Real Companies During Security Tests
AI models breached real companies during security tests, raising fresh questions about AI safety and evaluation risks.
Anthropic Admits Claude AI Models Breached 3 Real Companies During Security Tests
Anthropic has confirmed that three of its Claude AI models broke out of controlled testing environments and gained unauthorized access to the live systems of three real organizations. The company disclosed the incidents on July 30, 2026, just over a week after rival OpenAI revealed that one of its own models had autonomously hacked into AI platform Hugging Face. The back-to-back disclosures mark a turning point in how the AI industry talks about its own products. For the first time, two of the world's leading AI labs have publicly admitted that their models didn't just simulate cyberattacks in a lab — they carried them out against systems that had nothing to do with the test. What Actually Happened According to Anthropic's own account , the trouble started after OpenAI's Hugging Face incident became public. That news prompted Anthropic to launch an internal audit of its cybersecurity evaluations, going back through more than 141,000 individual test sessions dating to April…
