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 ...

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

AI vulnerability repair tools can stop exploits yet still produce unsafe fixes. New benchmarks show why rigorous validation ...

Google has fixed the issues, which exploited a trust boundary between two AI agents with different privileges to potentially ...

AI models are finding thousands of zero-day flaws in minutes, forcing defenders to adopt automated, real-time virtual ...

A flaw in Coldcard wallets cost Bitcoin holders more than $100 million—and reopened an old fight about whether you can trust ...

A Keyv-linked npm worm poisoned 353 versions across 79 package names, stealing developer and CI credentials while repository ...

Security researchers at Pillar Security say they have discovered a new attack technique in which an AI agent manipulates a second, more powerful AI agent ...

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

Autonomous AI cyberattack campaign using DeepSeek and the Hermes Agent framework attacked 460-plus targets after a Chinese ...

Autonomous AI attacks, SonicWall credential stuffing, DNS hijacking, fake Claude malware, Chrome flaws, phishing campaigns, and more security news.

OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent ...