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

Check Point researchers tried to break the frameworks enterprises use to build AI apps. Now they're telling Black Hat ...

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 ...

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

A roundup of the latest noteworthy AI-assisted attacks, threats, risks, and vulnerabilities, and what they portend for cyber defense.

Filters don't stop prompt injection; architecture does. A field guide to the lethal trifecta, the rule of two, Dual-LLM and ...

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

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

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

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

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

The flaws show how agentic workflows can turn trusted repository signals into privilege-escalation paths that conventional ...