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

In what they call the first-ever real-world agent-to-agent exploitation method, Pillar Security researchers say they discovered an exploit in the repository behind Google's Agent Development Kit for ...

The flaws show how agentic workflows can turn trusted repository signals into privilege-escalation paths that conventional identity and CI/CD controls may not reveal.

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

Contrary to expectations that multiple artificial intelligence (AI) agents would naturally collaborate when deployed in the ...

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

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

AI agent safety research from Anthropic's Frontier Red Team showed that individually aligned AI agents deployed self-replicating malware against each other in a shared environment, then hid the ...

Runtime intelligence startup FriskAI Inc. launched today with $3.6 million in pre-seed funding to give enterprises a record ...

The Open Secure AI Alliance introduced SAFE guidelines and open agent-security tools at Black Hat, giving enterprises a ...