Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

Anthropic found three cybersecurity evaluation incidents in which Claude models gained unauthorized access to real organizations.

Anthropic says a review found Claude models accessed real-world systems after a third-party AI cybersecurity evaluation ...

Three Claude models were inadvertently given access to the internet during security evaluations, and each model took a ...

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

Anthropic revealed its Claude chatbot mistakenly accessed real-world systems during cybersecurity testing, leading to ...

Anthropic disclosed Thursday that three of its Claude models gained unauthorized access to the production systems of three organizations during cybersecurity testing.

Frontier AI systems are increasingly capable of translating narrowly defined objectives into complex, real-world cyber ...

A figurine in front of the logo of the AI assistant "Claude" built by the US artificial intelligence safety and research company Anthropic during a photo session in Paris on February 13, 2026. Joel ...

Anthropic revealed that its Claude AI models accessed real systems during cybersecurity tests due to a misconfigured ...

Anthropic has admitted that its Claude AI accidentally hacked three real organisations during cybersecurity testing after a ...

OpenAI CEO Sam Altman (L), Anthropic CEO Dario Amodei (R) participate at a group photo at the AI Impact Summit in New Delhi on February 19, 2026. Ludovic MARIN/AFP via Getty Images Both arrived on ...