Anthropic says Claude AI models breached systems of 3 companies during cybersecurity tests

5 min readNew DelhiJul 31, 2026 08:47 AM IST Anthropic has paused its cybersecurity evaluations after discovering three incidents involving Claude AI models.(Image: Reuters)Amid the intensifying debate around autonomous AI systems and cybersecurity, frontier AI lab Anthropic, on Thursday, July 30, said that it had found three separate incidents where its Claude AI models gained access to the real systems of three organisations. The Dario Amodei-led company said that these discoveries were made during a large-scale retrospective review of its cybersecurity evaluations. The company admitted that the latest review was triggered by a similar security incident that was revealed by OpenAI last week.In a blog post, Anthropic detailed the security incidents, admitting that its Claude AI models had