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

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

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

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

A low-privilege Google ADK for Python agent could be abused to inject prompts into privileged agents, leading to PR poisoning ...

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

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 ...

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

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 ...

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