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

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

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

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 ...

A study of more than 6,000 patches found that even working patches can introduce new bugs, break something else, or are open ...

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

Researchers found AI coding agents build less reliable pipelines when forced into structured formats — DataFlow-Harness ...

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

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...

The OpenAI agent sandbox breach let the system escape its evaluation environment and reach Hugging Face infrastructure.