Most enterprises can't stop stage-three AI agent threats, VentureBeat survey finds

How mature is your AI agent security? VentureBeat's survey of 108 enterprises maps the gap between monitoring and isolation — ...

Capsule Security Exits Stealth With $7M to Stop AI Agents From Going Rogue at Runtime

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

Rogue AI agents exploit vulnerabilities, leak passwords, disable antivirus

AI agents are quickly moving from helpful assistants to autonomous doers that can browse the web, run scripts, manage files, and interact with enterprise tools. That power is also creating a new and ...
CIO

When AI goes rogue: Lessons from the Alibaba incident

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

A rogue AI agent started mining crypto, which left scientists concerned

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

Rogue AI Agent at Meta Causes Security Concerns — Report

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 ...
Business Insider

Operant AI Launches Agent ScopeGuard to Stop Rogue AI Agents Before They Cause Real-World Damage

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 ...