Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

For security teams, the adoption of agents showed up operationally before it showed up strategically - creating new expectations and requirements. Risk is no longer tied to prompts or the model alone. It shows up in what agents do once they are connected to critical systems - coming from permissions they inherit, tools they invoke, and data they move.

The OWASP GenAI Security Project has officially released its Top 10 for Agentic Applications, the first industry-standard framework focused on the operational risks created by autonomous and semi-autonomous AI systems. AI has evolved in a way that directly changes how enterprises need to think about security. We started with machine learning systems designed to classify and predict.

Data is never the problem. Security teams rarely complain about having too much of it. The real danger comes from data that sits unconnected and unexplained. What teams actually need is data that is actionable and converges into meaning. Data that cuts deeper than surface level signals. Data that reveals what is unfolding and what needs to happen next.

AI agents are increasingly connecting to more systems and workflows. They read structured data, follow multi-step instructions, and can reach deep into applications and developer environments. The same capabilities that make them powerful also create new opportunities for attackers. As Zenity Labs continued to study these emerging attack classes, we noticed a pattern starting to appear.

Agentic browsers are quickly becoming part of everyday work. Tools like ATLAS, Comet, and Dia can read web content, navigate SaaS tools, interpret instructions, and act on behalf of a user. They promise faster execution and higher productivity but they also introduce new risks that traditional security tools are not designed to see. As these browser-based agents spread across both managed and unmanaged devices, the enterprise attack surface grows in ways that most teams can’t quantify.

In the first installment of our Inside the Agent Stack series, we examined the design and security posture of agents built with Azure Foundry. Continuing the series, we now focus on Amazon Bedrock AgentCore, a managed service for building, deploying, and orchestrating AI agents on AWS.

Innovation has always been the engine of American advancement. With the launch of the Genesis Mission, the White House is signaling a new era of AI-accelerated scientific discovery. This executive order directs the Department of Energy to build an integrated, national-scale AI platform designed to unlock scientific breakthroughs across biotechnology, energy, materials, quantum systems, and beyond.

Financial services organizations are increasingly turning to AI agents to drive productivity, automate workflows, and deliver an innovative edge. Within the Microsoft ecosystem, two agentic platforms, Copilot Studio and Foundry, are paving new paths for agent development and deployment. Despite their shared vision for enterprise AI, their differences have important implications for user groups, agent capabilities, and security priorities.

This blog kicks off our new series, Inside the Agent Stack, where we take you behind the scenes of today’s most widely adopted AI agent platforms and show you what it really takes to secure them. Each installment will dissect a specific platform, expose realistic attack paths, and share proven strategies that help organizations keep their AI agents safe, reliable, and compliant.

Microsoft Foundry and Microsoft Copilot Studio have made it simple to build AI agents that automate workflows, access sensitive data, and integrate across critical business systems. However, agent democratization without control creates new security challenges. Further, as more agents are deployed across the organization, it means more agents that can access more data, invoke more tools (including MCP and A2A), and perform more actions. In other words, the potential attack surface is expanding.