Microsoft warns AI agents can become “double agents” when permissions sprawl and security lags. Memory poisoning and deceptive inputs can steer tools off course, so it recommends Zero Trust controls, ...

Microsoft and ServiceNow's exploitable agents reveal a growing - and preventable - AI security crisis ...

Copilot Studio agents are increasingly powerful. With that power comes risk: small misconfigurations, over‑broad sharing, ...

As companies expand their AI agent fleets, they’re discovering that managing them presents a new set of challenges. Microsoft aims to address those issues with Agent 365, a platform it launched at ...

New Microsoft Cyber Pulse report outlines why organizations should observe, govern, and secure their AI transformation to ...

You can now interact with 20 OneDrive files in one go, instead of file-by-file, with OneDrive's new AI Agents.

Microsoft has flagged serious security risks tied to AI agents in its latest Cyber Pulse Report, warning about so-called “AI double agents”. The report, published by the ...

Microsoft is adding Copilot-powered AI agents to OneDrive, enabling context-aware workflows across files and folders.

The thinking is that if AI gets the same treatment, it will be more difficult to exploit and less likely to become a security threat. It also means that employees will have a more difficult time using ...

Microsoft isn't breaking new ground in agentic AI, but it is presenting its agentic approach in a unified, sensible way that may resonate with business decision makers. What stuck out for me instead ...