On March 24, 2026, developers building AI applications with LiteLLM — a Python package with 95 million monthly downloads — ...

DOUBLECUP hides malware stages in cached PNG files, then uses ClickFix commands to deliver CountLoader variants and the ...

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 ...

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

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

Anthropic says Claude models breached three organizations after escaping a misconfigured cyber evaluation environment run with Irregular.

INC Ransomware is suspected of chaining CVE-2026-15409 and CVE-2026-15410 to steal credentials, TOTP seeds, and reach ...

Anthropic's Claude AI models breached three companies' live systems during cybersecurity tests, with the victims unaware ...

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

MCP is standardizing how AI agents connect to tools and data, replacing custom integrations with reusable servers. Here's how it works, with code.

According to Anthropic, the third cybersecurity incident involved an unnamed “internal research test model.” It compromised ...

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