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

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 ...

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

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

A researcher demonstrated a proof-of-concept attack chain that provided C2-style influence over ChatGPT's isolated sandbox at Black Hat USA 2026.

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

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

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

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 ...

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

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