Today, developers and security teams are caught in growing tension. AI is accelerating development and introducing new issues around insecure code, opaque models, data exposure, and compliance. Add the challenges of shadow AI and tool sprawl and the result is a widening gap between innovation and control. As developers move faster, security teams struggle to keep up with visibility, governance, and oversight. The resulting friction across the development lifecycle is forcing a tradeoff between speed and safety that doesn’t need to exist. Security needs to move upstream to become part of how developers actually work: built into their day-to-day tools and connected to the tools security teams use.

At Microsoft Build 2026, we are announcing new security tools and capabilities to give developers clear guidance in real time, scale with the complexity of tasks, and provide security teams with a consistent view across the full lifecycle so innovation can move fast and securely without the business losing control. Learn more about our solutions to help secure your code, secure your agents, and secure your models.

Secure your code

Today’s headlines reflect the tension around the power of AI models and the potential threat they pose when used to find and exploit vulnerabilities. It is forcing a shift as security teams look for solutions to help them safely harness the power of these models. At the same time, developers want to use these same models to efficiently identify real, exploitable risk and remediate it within their flow of work. That’s why we developed the Microsoft Security multi-model agentic scanning harness (codename MDASH) and added native integration between Microsoft Defender and GitHub Code Security (part of the former GitHub Advanced Security suite) to help both security and developer teams identify and close gaps early.

Discover and validate exploitable vulnerabilities with codename MDASH

The new Microsoft Security multi-model agentic scanning harness (codename MDASH) is available in an expanded preview for eligible organizations and now includes integration with Microsoft Defender. This new agentic security system orchestrates a pipeline of more than 100 specialized AI agents using an ensemble of models to discover, validate, and prove exploitability across codebases written in popular programming languages.

This approach is unique in the industry. Our multi-model agentic scanning harness uses a configurable panel of models, ranging from state-of-the-art (SOTA) models as the heavy reasoners, to more cost-effective models for high-volume operations. This allows us to trade speed, recall, and cost, and minimize dependency on any specific model.

The combination of multiple models, hundreds of agents, and over 100 trillion signals a day helps identify real risk over theoretical noise, to help teams focus on what can be exploited. The strategic implication is clear: AI vulnerability discovery has crossed from research curiosity into production-grade defense at enterprise scale, and the durable advantage lies in the agentic system around the model rather than any single model itself. MDASH recently jumped roughly 10% in less than three weeks to a new CyberGym industry benchmark score of 96.55%.

“At Accenture, we’re always looking toward the next frontier in protecting our clients and our enterprise. What Microsoft is building with MDASH reflects a meaningful shift from reactive, rule-based scanning to agentic systems that can reason across complex codebases like a skilled security researcher,” says Kris Burkhardt, Chief Information Security Officer at Accenture. Accenture is one of a select group of Security partners and Microsoft Intelligent Security Association (MISA) members that are engaged in the preview to shape MDASH and accelerate agentic AI vulnerability discovery.

Our partner engagements reflect a shared focus on moving from reactive detection to proactive identification of exploitable risk. “We’re seeing cyber threats evolve rapidly, with AI accelerating both the scale and sophistication of attacks. Microsoft’s investment in MDASH reflects a strong commitment to helping organizations stay ahead of this curve. Based on our early discussions and exposure to the innovation, we see strong potential for MDASH to simplify and strengthen SecOps, helping organizations operate with greater resilience and confidence,” says Morgan Adamski, Principal and Deputy Platform Leader of Cyber, Data, and Tech Risk at PwC US.

Together, we are partnering across the industry to use leading models paired with our platforms and expertise to deliver protection at scale. “We’re excited to work with Microsoft on MDASH because it addresses one of the most pressing challenges our customers face: reducing the time between discovering a vulnerability and taking meaningful action. Microsoft’s role as a trusted security vendor matters here—customers need innovation, but they also need confidence, governance, and a partner they can rely on. Our early experience with MDASH has been encouraging, and we see real opportunity for it to help organizations modernize how they approach vulnerability discovery and remediation,” says Jason Rader, Insight CISO.  

Reach out to your Microsoft account representative for more information on the expanded preview of codename MDASH.

Prioritize and remediate code vulnerabilities with Microsoft Defender and GitHub Code Security

While codename MDASH identifies and validates what’s truly exploitable, the integration between Microsoft Defender and GitHub Code Security (part of the former GitHub Advanced Security suite), now generally available, brings runtime context into development and security workflows so that teams can prioritize and address risks early minimizing the impact to human resources. Vulnerabilities discovered in code are automatically enriched with real production signals, such as internet exposure and data sensitivity to inform prioritization. Developers can then remediate issues using AI-assisted fixes that are generated, assigned, and validated through GitHub Copilot Autofix and the GitHub Copilot cloud agent.

To support responsible, coordinated disclosure of findings that represent both real and potential vulnerabilities, role-based access controls ensure that only authorized individuals can view and act on them. Together, the production signal enrichment, AI-assisted remediation, and secure handling of findings within a single workflow help security and developer teams focus on real risk and enable teams to act quickly.

Secure your agents

Agents are quickly becoming a new layer of the application stack. As developers build agents and move them into production, they need the tools to ship fast without sacrificing security, including built-in identity, governance, and safety testing. Security teams have overlapping needs: visibility into what’s running, control over what agents can access, and consistent governance across clouds and endpoints. Microsoft is delivering new solutions to help.

Build secure agents from day one

At Build 2026, Microsoft is introducing new capabilities to help developers build secure, enterprise-ready agents by default. With the general availability of the Agent 365 SDK, developers can integrate controls directly into their development workflows, bringing observability, access controls, and compliance enforcement into how agents are designed and deployed. This enables teams to build custom agents for any AI platform that are compliant, and enterprise-ready, and compose well with Agent 365.

Security extends beyond development and into how agents run. On Windows, the Microsoft Execution Container (MXC) SDK provides OS-level control over agent execution, giving developers and IT teams the ability to define containment and policy, applied by the OS through isolation technologies such as process and session isolation. Windows 365 for Agents, now generally available, enables you to run any agent in a fully isolated, policy-governed Cloud PC. Native Windows integration with Agent 365 provides a common foundation for observability, security, and governance, including built-in Intune capabilities to set policies that govern agent runtime execution and control how agents operate.

These new capabilities are now in early preview.

Observe, govern, and secure agents at scale with Agent 365—now including local agents

As agents proliferate across environments, gaining visibility and control over them becomes critical. Agent 365 introduces new capabilities to manage agent sprawl and risk, including an Agent 365 Agent Registry that surfaces unmanaged local agents discovered by Microsoft Defender, Microsoft Entra, and Microsoft Intune—all working together. The registry supports more than 20 types of local agents, including coding agents, AI desktop applications, and both local and remote Model Context Protocol (MCP) servers. From there, Intune policies can be used to block common execution methods for OpenClaw agents.

Security teams also need the ability to defend against emerging threats without slowing developer productivity. Microsoft Defender, Entra, and Intune work together to provide the visibility, runtime protections, and context needed to manage agent risk without slowing developer productivity. Defender enables analysts to investigate agent activity using advanced hunting and provides an exposure graph that helps teams understand how agents are connected across the network. Preview of these capabilities coming soon.

Protecting data is foundational to securing agents at scale. Microsoft Purview controls to prevent data exfiltration, Data Security Posture Management risk discovery, and agentic risk detection for coding agents Claude Code, GitHub Copilot, OpenAI Codex, and OpenClaw. This enables visibility on how local agents access sensitive data, runtime protections for risky prompts, and insights into unsafe agent behaviors. Microsoft Purview Audit also logs all agent activity for full traceability. Preview of these capabilities coming soon.

Trust agents with your data

Developers also need direct, real-time insight into data security posture and risk signals associated with the agents they build. With Purview data risk signals embedded in the Foundry Control Plane, generally available, these signals provide guidance to developers on where to enforce protections before sensitive data is exposed. For example, Purview flags in real time when an agent surfaces sensitive financial data during testing and guides developers to mask or restrict access before deployment.

To further reduce risk, Purview introduces runtime data loss prevention (DLP) for agent prompts in Foundry, in preview with Agent 365. This capability detects, blocks, and audits sensitive data before it is processed by the agent, ensuring that sensitive information never reaches AI models.

Secure your models

Before AI reaches production, teams need to verify that the models they depend on are safe. Now developers can inspect model artifacts, whether platform-native or bring-your-own, with Defender AI model scanning, in preview. To help close gaps early model Defender AI model scanning detects and blocks potentially vulnerable or compromised models across registries, workspaces, and CI/CD pipelines to verify model integrity before deployment.

Trust starts with security

There should never be a choice between innovation and safety.

The capabilities announced today span the full development lifecycle: discovering what’s exploitable, governing what’s running, protecting the data AI depends on, and verifying that agents behave as intended before they reach production. Microsoft security is embedded directly into the platforms and workflows developers already use, supporting innovation across Microsoft Foundry, Copilot Studio, GitHub, and open-source frameworks, and bringing discovery and governance to shadow AI.

But real progress in AI depends on more than breakthrough capabilities—it depends on whether organizations can trust the systems they are building and deploying. That is the common thread across the innovations announced at Build 2026 and the principle guiding our approach. Because the future of AI will belong not just to those who move fastest, but to those who can innovate with trust.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity. To learn more about how security is built into the Windows platform, explore the Windows Security book and Windows Server Security book.

The post Microsoft Build 2026: Securing code, agents, and models across the development lifecycle appeared first on Microsoft Security Blog.

Lawmakers in both houses of Congress are demanding answers from the U.S. Cybersecurity & Infrastructure Security Agency (CISA) after KrebsOnSecurity reported this week that a CISA contractor intentionally published AWS GovCloud keys and a vast trove of other agency secrets on a public GitHub account. The inquiry comes as CISA is still struggling to contain the breach and invalidate the leaked credentials.

On May 18, KrebsOnSecurity reported that a CISA contractor with administrative access to the agency’s code development platform had created a public GitHub profile called “Private-CISA” that included plaintext credentials to dozens of internal CISA systems. Experts who reviewed the exposed secrets said the commit logs for the code repository showed the CISA contractor disabled GitHub’s built-in protection against publishing sensitive credentials in public repos.

CISA acknowledged the leak but has not responded to questions about the duration of the data exposure. However, experts who reviewed the now-defunct Private-CISA archive said it was originally created in November 2025, and that it exhibits a pattern consistent with an individual operator using the repository as a working scratchpad or synchronization mechanism rather than a curated project repository.

In a written statement, CISA said “there is no indication that any sensitive data was compromised as a result of the incident.” But in a May 19 a letter (PDF) to CISA’s Acting Director Nick Andersen, Sen. Maggie Hassan (D-NH) said the credential leak raises serious questions about how such a security lapse could occur at the very agency charged with helping to prevent cyber breaches.

“This reporting raises serious concerns regarding CISA’s internal policies and procedures at a time of significant cybersecurity threats against U.S. critical infrastructure,” Sen. Hassan wrote.

Sen. Hassan noted that the incident occurred against the backdrop of major disruptions internally at CISA, which lost more than a third of it workforce and almost all of its senior leaders after the Trump administration forced a series of early retirements, buyouts, and resignations across the agency’s various divisions.

Rep. Bennie Thompson (D-MS), the ranking member on the House Homeland Security Committee, echoed the senator’s concerns.

“We are concerned that this incident reflects a diminished security culture and/or an inability for CISA to adequately manage its contract support,” Thompson wrote in a May 19 letter to the acting CISA chief that was co-signed by Rep. Delia Ramirez (D-Ill), the ranking member of the panel’s Subcommittee on Cybersecurity and Infrastructure Protection. “It’s no secret that our adversaries — like China, Russia, and Iran — seek to gain access to and persistence on federal networks. The files contained in the ‘Private-CISA’ repository provided the information, access, and roadmap to do just that.”

KrebsOnSecurity has learned that more a week after CISA was first notified of the data leak by the security firm GitGuardian, the agency is still working to invalidate and replace many of the exposed keys and secrets.

On May 20, KrebsOnSecurity heard from Dylan Ayrey, the creator of TruffleHog, an open-source tool for discovering private keys and other secrets buried in code hosted at GitHub and other public platforms. Ayrey said CISA still hadn’t invalidated an RSA private key exposed in the Private-CISA repo that granted access to a GitHub app which is owned by the CISA enterprise account and installed on the CISA-IT GitHub organization with full access to all code repositories.

“An attacker with this key can read source code from every repository in the CISA-IT organization, including private repos, register rogue self-hosted runners to hijack CI/CD pipelines and access repository secrets, and modify repository admin settings including branch protection rules, webhooks, and deploy keys,” Ayrey told KrebsOnSecurity. CI/CD stands for Continuous Integration and Continuous Delivery, and it refers to a set of practices used to automate the building, testing and deployment of software.

KrebsOnSecurity notified CISA about Ayrey’s findings on May 20. Ayrey said CISA appears to have invalidated the exposed RSA private key sometime after that notification. But he noted that CISA still hasn’t rotated leaked credentials tied to other critical security technologies that are deployed across the agency’s technology portfolio (KrebsOnSecurity is not naming those technologies publicly for the time being).

CISA responded with a brief written statement in response to questions about Ayrey’s findings, saying “CISA is actively responding and coordinating with the appropriate parties and vendors to ensure any identified leaked credentials are rotated and rendered invalid and will continue to take appropriate steps to protect the security of our systems.”

Ayrey said his company Truffle Security monitors GitHub and a number of other code platforms for exposed keys, and attempts to alert affected accounts to the sensitive data exposure(s). They can do this easily on GitHub because the platform publishes a live feed which includes a record of all commits and changes to public code repositories. But he said cybercriminal actors also monitor these public feeds, and are often quick to pounce on API or SSH keys that get inadvertently published in code commits.

In practical terms, it is likely that cybercrime groups or foreign adversaries also noticed the publication of these CISA secrets, the most egregious of which appears to have happened in late April 2026, Ayrey said.

“We monitor that firehose of data for keys, and we have tools to try to figure out whose they are,” he said. “We have evidence attackers monitor that firehose as well. Anyone monitoring GitHub events could be sitting on this information.”

James Wilson, the enterprise technology editor for the Risky Business security podcast, said organizations using GitHub to manage code projects can set top-down policies that prevent employees from disabling GitHub’s protections against publishing secret keys and credentials. But Wilson’s co-host Adam Boileau said it’s not clear that any technology could stop employees from opening their own personal GitHub account and using it to store sensitive and proprietary information.

“Ultimately, this is a thing you can’t solve with a technical control,” Boileau said on this week’s podcast. “This is a human problem where you’ve hired a contractor to do this work and they have decided of their own volition to use GitHub to synchronize content from a work machine to a home machine. I don’t know what technical controls you could put in place given that this is being done presumably outside of anything CISA managed or even had visibility on.”

Update, 3:05 p.m. ET: Added statement from CISA. Corrected a date in the story (Truffle Security said it found the repo gained some of its most sensitive secrets in late April 2026, not 2025).