Identity

Silverfort integrates identity controls with Microsoft Copilot Studio agents

A robotic hand interacts with a keyboard amidst digital security icons, showcasing advancements in cyber security and the relationship between technology and safety.

According to Silicon Angle, Silverfort Inc. has launched an integration that applies its identity and access controls to artificial intelligence agents within Microsoft Corp.’s Copilot Studio, aiming to enforce policies at the moment an agent attempts an action.

The new integration evaluates every access request made by a Copilot agent in real time, providing a decision before the action is executed. This prevents agents from gaining unauthorized access or escalating their privileges. The solution ensures that AI agents cannot exceed their authorized permissions, blocks anomalous access attempts, and adapts policies based on real-time context. The platform provides a unified control plane across different agent types, extending visibility and enforcement to human identities, service accounts, and external agents.

This initiative follows Silverfort's acquisition of Fabrix Security Ltd. and aims to enhance AI security by detecting threats like prompt injection and jailbreak attempts. The integration is currently available through an early access program.

Source: Silicon Angle

Get daily email updates

SC Media's daily must-read of the most current and pressing daily news

By clicking the Subscribe button below, you agree to SC Media Terms of Use and Privacy Policy.

You can skip this ad in 5 seconds