Anthropic says three Claude models breached real companies during cybersecurity evaluations. Ordinary weaknesses, chained ...

In what they call the first-ever real-world agent-to-agent exploitation method, Pillar Security researchers say they ...

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing ...

AI agent tool bypass vulnerability CoreBreak exposed production agent infrastructure at AWS, Google, and Vercel, where attackers could invoke tools without any model turn. AWS fixed its managed ...

One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security ...

The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...

AI agent flaws in AWS, Google, and Vercel let forged tool calls reach tools without model authorization, while several paths ...

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

Discover the best open-source vulnerability scanners of 2026 that help CIOs minimize security costs while ensuring robust protection against software vulnerabilities. Learn about their features and ...

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

It was a bad idea.

Written by Ken Huang, CEO & Chief AI Officer, DistributedApps.ai. Two evaluation escapes in one week. Mapped onto the seven MAESTRO layers, one is an operations failure, and the other is an alignment ...