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

ARC-AGI-3 benchmark gains its first fully open-source agent: NIMI's Tycho writes Python code as falsifiable hypotheses about ...

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

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 ...

Google removed 3 ADK AI workflows after Pillar showed a public GitHub issue could trigger a privileged agent & reach code ...

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

Twelve datasets and evaluation systems, built by hand from thousands of real-world security flaws, give model builders and ...

At Black Hat USA, Zenity Labs today announced new research detailing an active credential-stealing malicious skills campaign distributed through Vercel's skills.sh. The affected skill family amassed ...

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

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to breach the servers running them and make off with sensitive data and ...

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

NVIDIA and 36 other industry partners are targeting agent security across multi-vendor clouds by combining open technologies for workload identity, agent controls, vulnerability scanning, and software ...