Add Yahoo as a preferred source to see more of our stories on Google. Meta is reviewing reports that an internal AI agent exposed sensitive company information to unauthorized employees, raising ...

In cybersecurity, the most important lessons rarely come from theory, but from reality. A recent incident involving an ...

Capsule Security, a trust layer for agentic AI, today launched from stealth with a $7 million seed round led by Lama Partners ...

Agentic AI is growing increasingly sophisticated, but when an AI agent started spontaneously cryptomining, researchers were understandably concerned.

A new study finds that AI agents can act to preserve other bots even when that behavior conflicts with their assigned task. Why it matters: Just because Sam Altman and Dario Amodei won't hold hands, ...

AI agents work together to bypass security controls and stealthily steal sensitive data from within the enterprise systems in which they operate, according to tests carried out by frontier security ...

SAN FRANCISCO, March 23, 2026 (GLOBE NEWSWIRE) -- Operant AI, a Gartner-recognized leader in AI and Agentic security, today announced the launch of Agent ScopeGuard, a new capability for Operant’s ...

Meta is facing a security concern after an AI agent reportedly went rogue and exposed sensitive company information to employees who did not have permission to access it. As per reports, this happened ...