Enterprise-grade controls for AI apps and agents built with Azure AI Foundry and Copilot Studio
AI innovation is moving faster than ever, and more AI projects are moving beyond experimentation into deployment, to drive tangible business impact. As organizations accelerate innovation with custom AI applications and agents, new risks emerge across the software development lifecycle and AI stack related to data oversharing and leaks, new vulnerabilities and threats, and non-compliance with stringent regulatory requirements Through 2025, poisoning of software supply chains and infrastructure technology stacks will constitute more than 70% of malicious attacks against AI used in the enterprise 1 , highlighting potential threats that originate early in development. Today, the average cost of a data breach is $4.88 million, but when security issues are caught early in the development process, that number drops dramatically to just $80 per incident 2 . The message is very clear; security can’t be an afterthought anymore. It must be a team sport across the organization, embedded from the start and throughout the development lifecycle. That's why developers and security teams should align on processes and tools that bring security into every stage of the AI development lifecycle and give security practitioners visibility into and the ability to mitigate risks. To address these growing challenges and help customers secure and govern their AI workloads across development and security teams, we are: Enabling Azure AI Foundry and Microsoft Copilot Studio to provide best-in-class foundational capabilities to secure and govern AI workloads Deeply integrating and embedding industry-leading capabilities from Microsoft Purview, Microsoft Defender, and Microsoft Entra into Azure AI Foundry and Microsoft Copilot Studio This week, 3,000 developers are gathering in Seattle for the annual Microsoft Build conference, with many more tuning in online, to learn practical skills for accelerating their AI apps and agents' innovation. To support their AI innovation journey, today we are excited to announce several new capabilities to help developers and organizations secure and govern AI apps and agents. New Azure AI Foundry foundational capabilities to secure and govern AI workloads Azure AI Foundry enhancements for AI security and safety With 70,000 customers, 100 trillion tokens processed this quarter, and 2 billion enterprise search queries each day, Azure AI Foundry has grown beyond just an application layer—it's now a comprehensive platform for building agents that can plan, take action, and continuously learn to drive real business outcomes. To help organizations build and deploy AI with confidence, we’re introducing new security and safety capabilities and insights for developers in Azure AI Foundry Introducing Spotlighting to detect and block prompt injection attacks in real time As AI systems increasingly rely on external data sources, a new class of threats has emerged. Indirect prompt injection attacks embed hidden instructions in documents, emails, and web content, tricking models into taking unauthorized actions without any direct user input. These attacks are difficult to detect and hard to prevent using traditional filters alone. To address this, Azure AI Content Safety is introducing Spotlighting, now available in preview. Spotlighting strengthens the Prompt Shields guardrail by improving its ability to detect and handle potential indirect prompt injections, where hidden adversarial instructions are embedded in external content. This new capability helps prevent the model from inadvertently acting on malicious prompts that are not directly visible to the user. Enable Spotlighting in Azure AI Content Safety to detect potential indirect prompt injection attacks New capabilities for task adherence evaluation and task adherence mitigation to ensure agents remain within scope As developers build more capable agents, organizations face growing pressure to help confirm those agents act within defined instructions and policy boundaries. Even small deviations can lead to tool misuse, broken workflows, or risks like unintended exposure of sensitive data. To solve this, Azure AI Foundry now includes task adherence for agents, now in preview and powered by two components: a real-time evaluation and a new control within Azure AI Content Safety. At the core is a real-time task adherence evaluation API, part of Azure AI Content Safety. This API assesses whether an agent’s behavior is aligned with its assigned task by analyzing the user’s query, system instructions, planned tool calls, and the agent’s response. The evaluation framework is built on Microsoft’s Agent Evaluators, which measure intent resolution, tool selection accuracy, completeness of response, and overall alignment to the original request. Developers can run this scoring logic locally using the Task Adherence Evaluator in the Azure AI Evaluation SDK, with a five-point scale that ranges from fully nonadherent to fully adherent. This gives teams a flexible and transparent way to inspect task-level behavior before it causes downstream issues. Task adherence is enforced through a new control in Azure AI Content Safety. If an agent goes off-task, the control can block tool use, pause execution, or trigger human review. In Azure AI Agent Service, it is available as an opt-in feature and runs automatically. Combined with real-time evaluation, this control helps to ensure that agents stay on task, follow instructions, and operate according to enterprise policies. Learn more about Prompt Shields in Azure AI Content Safety. Azure AI Foundry continuous evaluation and monitoring of agentic systems Maintaining high performance and compliance for AI agents after deployment is a growing challenge. Without ongoing oversight, issues like performance degradation, safety risks, or unintentional misuse of resources can slip through unnoticed. To address this, Azure AI Foundry introduces continuous evaluation and monitoring of agentic systems, now in preview, provides a single pane of glass dashboard to track key metrics such as performance, quality, safety, and resource usage in real time. Continuous evaluation runs quality and safety evaluations at a sampled rate of production usage with results made available in the Azure AI Foundry Monitoring dashboard and published to Application Insights. Developers can set alerts to detect drift or regressions and use Azure Monitor to gain full-stack visibility into their AI systems. For example, an organization using an AI agent to assist with customer-facing tasks can monitor groundedness and detect a decline in quality when the agent begins referencing irrelevant information, helping teams to act before it potentially negatively affects trust of users. Azure AI Foundry evaluation integrations with Microsoft Purview Compliance Manager, Credo.AI, and Saidot for streamlined compliance AI regulations and standards introduce new requirements for transparency, documentation, and risk management for high-risk AI systems. As developers build AI applications and agents, they may need guidance and tools to help them evaluate risks based on these requirements and seamlessly share control and evaluation insights with compliance and risk teams. Today, we are announcing previews for Azure AI Foundry evaluation tool’s integration with a compliance management solution, Microsoft Purview Compliance Manager, and AI governance solutions, Credo.AI and Saidot. These integrations help define risk parameters, run suggested compliance evaluations, and collect evidence for control testing and auditing. For example, for a developer who’s building an AI agent in Europe may be required by their compliance team to complete a Data Protection Impact Assets (DPIA) and Algorithmic Impact Assessment (AIA) to meet internal risk management and technical documentation requirements aligned with emerging AI governance standards and best practices. Based on Purview Compliance Manager’s step-by-step guidance on controls implementation and testing, the compliance teams can evaluate risks such as potential bias, cybersecurity vulnerabilities, or lack of transparency in model behavior. Once the evaluation is conducted in Azure AI Foundry, the developer can obtain a report with documented risk, mitigation, and residual risk for compliance teams to upload to Compliance Manager to support audits and provide evidence to regulators or external stakeholders. Assess controls for Azure AI Foundry against emerging AI governance standards Learn more about Purview Compliance Manager. Learn more about the integration with Credo.AI and Saidot in this blogpost. Leading Microsoft Entra, Defender and Purview value extended to Azure AI Foundry and Microsoft Copilot Studio Introducing Microsoft Entra Agent ID to help address agent sprawl and manage agent identity Organizations are rapidly building their own AI agents, leading to agent sprawl and a lack of centralized visibility and management. Security teams often struggle to keep up, unable to see which agents exist and whether they introduce security or compliance risks. Without proper oversight, agent sprawl increases the attack surface and makes it harder to manage these non-human identities. To address this challenge, we’re announcing the public preview of Microsoft Entra Agent ID, a new capability in the Microsoft Entra admin center that gives security admins visibility and control over AI agents built with Copilot Studio and Azure AI Foundry. With Microsoft Entra Agent ID, an agent created through Copilot Studio or Azure AI Foundry is automatically assigned an identity with no additional work required from the developers building them. This is the first step in a broader initiative to manage and protect non-human identities as organizations continue to build AI agents. : Security and identity admins can gain visibility into AI agents built in Copilot Studio and Azure AI Foundry in the Microsoft Entra Admin Center This new capability lays the foundation for more advanced capabilities coming soon to Microsoft Entra. We also know that no one can do it alone. Security has always been a team sport, and that’s especially true as we enter this new era of protecting AI agents and their identities. We’re energized by the momentum across the industry; two weeks ago, we announced support for the Agent-to-Agent (A2A) protocol and began collaborating with partners to shape the future of AI identity workflows. Today, we’re also excited to announce new partnerships with ServiceNow and Workday. As part of this, we’ll integrate Microsoft Entra Agent ID with the ServiceNow AI Platform and the Workday Agent System of Record. This will allow for automated provisioning of identities for future digital employees. Learn more about Microsoft Entra Agent ID. Microsoft Defender security alerts and recommendations now available in Azure AI Foundry As more AI applications are deployed to production, organizations need to predict and prevent potential AI threats with natively integrated security controls backed by industry-leading Gen AI and threat intelligence for AI deployments. Developers need critical signals from security teams to effectively mitigate security risks related to their AI deployments. When these critical signals live in separate systems outside the developer experience, this can create delays in mitigation, leaving opportunities for AI apps and agents to become liabilities and exposing organizations to various threats and compliance violations. Now in preview, Microsoft Defender for Cloud integrates AI security posture management recommendations and runtime threat protection alerts directly into the Azure AI Foundry portal. These capabilities, previously announced as part of the broader Microsoft Defender for Cloud solution, are extended natively into Azure AI Foundry enabling developers to access alerts and recommendations without leaving their workflows. This provides real-time visibility into security risks, misconfigurations, and active threats targeting their AI applications on specific Azure AI projects, without needing to switch tools or wait on security teams to provide details. Security insights from Microsoft Defender for Cloud help developers identify and respond to threats like jailbreak attacks, sensitive data leakage, and misuse of system resources. These insights include: AI security posture recommendations that identify misconfigurations and vulnerabilities in AI services and provide best practices to reduce risk Threat protection alerts for AI services that notify developers of active threats and provide guidance for mitigation, across more than 15 detection types For example, a developer building an AI-powered agent can receive security recommendations suggesting the use of Azure Private Link for Azure AI Services resources. This reduces the risk of data leakage by handling the connectivity between consumers and services over the Azure backbone network. Each recommendation includes actionable remediation steps, helping teams identify and mitigate risks in both pre- and post-deployment phases. This helps to reduce risks without slowing down innovation. : Developers can view security alerts on the Risks + alerts page in Azure AI Foundry : Developers can view recommendations on the Guardrails + controls page in Azure AI Foundry This integration is currently in preview and will be generally available in June 2025 in Azure AI Foundry. Learn more about protecting AI services with Microsoft Defender for Cloud. Microsoft Purview capabilities extended to secure and govern data in custom-built AI apps and agents Data oversharing and leakage are among the top concerns for AI adoption, and central to many regulatory requirements. For organizations to confidently deploy AI applications and agents, both low code and pro code developers need a seamless way to embed security and compliance controls into their AI creations. Without simple, developer-friendly solutions, security gaps can quickly become blockers, delaying deployment and increasing risks as applications move from development to production. Today, Purview is extending its enterprise-grade data security and compliance capabilities, making it easier for both low code and pro code developers to integrate data security and compliance into their AI applications and agents, regardless of which tools or platforms they use. For example, with this update, Microsoft Purview DSPM for AI becomes the one place data security teams can see all the data risk insights across Microsoft Copilots, agents built in Agent Builder and Copilot Studio, and custom AI apps and agents built in Azure AI Foundry and other platforms. Admins can easily drill into security and compliance insights for specific AI apps or agents, making it easier to investigate and take action on potential risks. : Data security admins can now find data security and compliance insights across Microsoft Copilots, agents built with Agent Builder and Copilot Studio, and custom AI apps and agents in Microsoft Purview DSPM for AI In the following sections, we will provide more details about the updates to Purview capabilities in various AI workloads. 1. Microsoft Purview data security and compliance controls can be extended to any custom-built AI application and agent via the new Purview SDK or the native Purview integration with Azure AI Foundry. The new capabilities make it easy and effortless for security teams to bring the same enterprise-grade data security compliance controls available today for Microsoft 365 Copilot to custom AI applications and agents, so organizations can: Discover data security risks, such as sensitive data in user prompts, and data compliance risks, such as harmful content, and get recommended actions to mitigate risks proactively in Microsoft Purview Data Security Posture Management (DSPM) for AI. Protect sensitive data against data leakage and insider risks with Microsoft Purview data security policies. Govern AI interactions with Audit, Data Lifecycle Management, eDiscovery, and Communication Compliance. Microsoft Purview SDK Microsoft Purview now offers Purview SDK, a set of REST APIs, documentation, and code samples, currently in preview, enabling developers to integrate Purview's data security and compliance capabilities into AI applications or agents within any integrated development environment (IDE). : By embedding Purview APIs into the IDE, developers help enable their AI apps to be secured and governed at runtime For example, a developer building an AI agent using an AWS model can use the Purview SDK to enable their AI app to automatically identify and block sensitive data entered by users before it’s exposed to the model, while also providing security teams with valuable signals that support compliance. With Purview SDK, startups, ISVs, and partners can now embed Purview industry-leading capabilities directly into their AI software solutions, making these solutions Purview aware and easier for their customers to secure and govern data in their AI solutions. For example, Infosys Vice President and Delivery Head of Cyber Security Practice, Ashish Adhvaryu indicates, “Infosys Cyber Next platform integrates Microsoft Purview to provide enhanced AI security capabilities. Our solution, the Cyber Next AI assistant (Cyber Advisor) for the SOC analyst, leverages Purview SDK to drive proactive threat mitigation with real-time monitoring and auditing capabilities. This integration provides holistic AI-assisted protection, enhancing cybersecurity posture." Microsoft partner EY (previously known as Ernst and Young) has also leveraged the new Purview SDK to embed Purview value into their GenAI initiatives. “We’re not just building AI tools, we are creating Agentic solutions where trust, security, and transparency are present from the start, supported by the policy controls provided through the Purview SDK. We’re seeing 25 to 30 percent time savings when we build secure features using the Purview SDK,” noted Sumanta Kar, Partner, Innovation and Emerging Tech at EY. Learn more about the Purview SDK. Microsoft Purview integrates natively with Azure AI Foundry Organizations are developing an average of 14 custom AI applications. The rapid pace of AI innovation may leave security teams unaware of potential data security and compliance risks within their environments. With the update announced today, Azure AI Foundry signals are now directly integrated with Purview Data Security Posture Management for AI, Insider Risk Management, and data compliance controls, minimizing the need for additional development work. For example, for AI applications and agents built with Azure AI Foundry models, data security teams can gain visibility into AI usage and data risks in Purview DSPM for AI, with no additional work from developers. Data security teams can also detect, investigate, and respond to both malicious and inadvertent user activities, such as a departing employee leveraging an AI agent to retrieve an anomalous amount of sensitive data, with Microsoft Purview Insider Risk Management (IRM) policies. Lastly, user prompts and AI responses in Azure AI apps and agents can now be ingested into Purview compliance tools as mentioned above. Learn more about Microsoft Purview for Azure AI Foundry. 2. Purview data protections extended to Copilot Studio agents grounded in Microsoft Dataverse data Coming to preview in June, Purview Information Protection extends auto-labeling and label inheritance coverage to Dataverse to help prevent oversharing and data leaks. Information Protection makes it easier for organizations to automatically classify and protect sensitive data at scale. A common challenge is that sensitive data often lands in Dataverse from various sources without consistent labeling or protection. The rapid adoption of agents built using Copilot Studio and grounding data from Dataverse increases the risk of data oversharing and leakage if data is not properly protected. With auto-labeling, data stored in Dataverse tables can be automatically labeled based on policies set in Microsoft Purview, regardless of its source. This reduces the need for manual labeling effort and protects sensitive information from the moment it enters Dataverse. With label inheritance, AI agent responses grounded in Dataverse data will automatically carry and honor the source data’s sensitivity label. If a response pulls from multiple tables with different labels, the most restrictive label is applied to ensure consistent protection. For example, a financial advisor building an agent in Copilot Studio might connect multiple Dataverse tables, some labeled as “General” and others as “Highly Confidential.” If a response pulls from both, it will inherit the most restrictive label, in this case, "Highly Confidential,” to prevent unauthorized access and ensure appropriate protections are applied across both maker and users of the agent. Together, auto-labeling and label inheritance in Dataverse support a more secure, automated foundation for AI. : Sensitivity labels will be automatically applied to data in Dataverse : AI-generated responses will inherit and honor the source data’s sensitivity labels Learn more about protecting Dataverse data with Microsoft Purview. 3. Purview DSPM for AI can now provide visibility into unauthenticated interactions with Copilot Studio agents As organizations increasingly use Microsoft Copilot Studio to deploy AI agents for frontline customer interactions, gaining visibility into unauthenticated user interactions and proactively mitigating risks becomes increasingly critical. Building on existing Purview and Copilot Studio integrations, we’ve extended DSPM for AI and Audit in Copilot Studio to provide visibility into unauthenticated interactions, now in preview. This gives organizations a more comprehensive view of AI-related data security risks across authenticated and unauthenticated users. For example, a healthcare provider hosting an external, customer-facing agent assistant must be able to detect and respond to attempts by unauthenticated users to access sensitive patient data. With these new capabilities in DSPM for AI, data security teams can now identify these interactions, assess potential exposure of sensitive data, and act accordingly. Additionally, integration with Purview Audit provides teams with seamless access to information needed for audit requirements. : Gain visibility into all AI interactions, including those from unauthenticated users Learn more about Purview for Copilot Studio. 4. Purview Data Loss Prevention extended to more Microsoft 365 agent scenarios To help organizations prevent data oversharing through AI, at Ignite 2024, we announced that data security admins could prevent Microsoft 365 Copilot from using certain labeled documents as grounding data to generate summaries or responses. Now in preview, this control also extends to agents published in Microsoft 365 Copilot that are grounded by Microsoft 365 data, including pre-built Microsoft 365 agents, agents built with the Agent Builder, and agents built with Copilot Studio. This helps ensure that files containing sensitive content are used appropriately by AI agents. For example, confidential legal documents with highly specific language that could lead to improper guidance if summarized by an AI agent, or "Internal only” documents that shouldn’t be used to generate content that can be shared outside of the organization. : Extend data loss prevention (DLP) policies to Microsoft 365 Copilot agents to protect sensitive data Learn more about Data Loss Prevention for Microsoft 365 Copilot and agents. The data protection capabilities we are extending to agents in Agent Builder and Copilot Studio demonstrate our continued investment in strengthening the Security and Governance pillar of the Copilot Control System (CSS). CCS provides integrated controls to help IT and security teams secure, manage, and monitor Copilot and agents across Microsoft 365, spanning governance, management, and reporting. Learn more here. Explore additional resources As developers and security teams continue to secure AI throughout its lifecycle, it’s important to stay ahead of emerging risks and ensure protection. Microsoft Security provides a range of tools and resources to help you proactively secure AI models, apps, and agents from code to runtime. Explore the following resources to deepen your understanding and strengthen your approach to AI security: Learn more about Security for AI solutions on our webpage Learn more about Microsoft Purview SDK Get started with Azure AI Foundry Get started with Microsoft Entra Get started with Microsoft Purview Get started with Microsoft Defender for Cloud Get started with Microsoft 365 Copilot Get started with Copilot Studio Sign up for a free Microsoft 365 E5 Security Trial and Microsoft Purview Trial 1 Predicts 2025: Navigating Imminent AI Turbulence for Cybersecurity, Jeremy D'Hoinne, Akif Khan, Manuel Acosta, Avivah Litan, Deepak Seth, Bart Willemsen, 10 February 2025 2 IBM. "Cost of a Data Breach 2024: Financial Industry." IBM Think, 13 Aug. 2024, https://www.ibm.com/think/insights/cost-of-a-data-breach-2024-financial-industry; Cser, Tamas. "The Cost of Finding Bugs Later in the SDLC." Functionize, 5 Jan. 2023, https://www.functionize.com/blog/the-cost-of-finding-bugs-later-in-the-sdlcUnderstanding and mitigating security risks in MCP implementations
Introducing any new technology can introduce new security challenges or exacerbate existing security risks. In this blog post, we’re going to look at some of the security risks that could be introduced to your environment when using Model Context Protocol (MCP), and what controls you can put in place to mitigate them. MCP is a framework that enables seamless integration between LLM applications and various tools and data sources. MCP defines: A standardized way for AI models to request external actions through a consistent API Structured formats for how data should be passed to and from AI systems Protocols for how AI requests are processed, executed, and returned MCP allows different AI systems to use a common set of tools and patterns, ensuring consistent behavior when AI models interact with external systems. MCP architecture MCP follows a client-server architecture that allows AI models to interact with external tools efficiently. Here’s how it works: MCP Host – The AI model (e.g., Azure OpenAI GPT) requesting data or actions. MCP Client – An intermediary service that forwards the AI model's requests to MCP servers. MCP Server – Lightweight applications that expose specific capabilities (APIs, databases, files, etc.). Data Sources – Various backend systems, including local storage, cloud databases, and external APIs. MCP security controls Any system which has access to important resources has implied security challenges. Security challenges can generally be addressed through correct application of fundamental security controls and concepts. As MCP is only newly defined, the specification is changing very rapidly and as the protocol evolves. Eventually the security controls within it will mature, enabling a better integration with enterprise and established security architectures and best practices. Research published in the Microsoft Digital Defense Report states that 98% of reported breaches would be prevented by robust security hygiene and the best protection against any kind of breach is to get your baseline security hygiene, secure coding best practices and supply chain security right – those tried and tested practices that we already know about still make the most impact in reducing security risk. Let's look at some of the ways that you can start to address security risks when adopting MCP. MCP server authentication (if your MCP implementation was before 26th April 2025) Problem statement: The original MCP specification assumed that developers would write their own authentication server. This requires knowledge of OAuth and related security constraints. MCP servers acted as OAuth 2.0 Authorization Servers, managing the required user authentication directly rather than delegating it to an external service such as Microsoft Entra ID. As of 26 April 2025, an update to the MCP specification allows for MCP servers to delegate user authentication to an external service. Risks: Misconfigured authorization logic in the MCP server can lead to sensitive data exposure and incorrectly applied access controls. OAuth token theft on the local MCP server. If stolen, the token can then be used to impersonate the MCP server and access resources and data from the service that the OAuth token is for. Mitigating controls: Thoroughly review your MCP server authorization logic, here some posts discussing this in more detail - Azure API Management Your Auth Gateway For MCP Servers | Microsoft Community Hub and Using Microsoft Entra ID To Authenticate With MCP Servers Via Sessions · Den Delimarsky Implement best practices for token validation and lifetime Use secure token storage and encrypt tokens Excessive permissions for MCP servers Problem statement: MCP servers may have been granted excessive permissions to the service/resource they are accessing. For example, an MCP server that is part of an AI sales application connecting to an enterprise data store should have access scoped to the sales data and not allowed to access all the files in the store. Referencing back to the principle of least privilege (one of the oldest security principles), no resource should have permissions in excess of what is required for it to execute the tasks it was intended for. AI presents an increased challenge in this space because to enable it to be flexible, it can be challenging to define the exact permissions required. Risks: Granting excessive permissions can allow for exfiltration or amending data that the MCP server was not intended to be able to access. This could also be a privacy issue if the data is personally identifiable information (PII). Mitigating controls: Clearly define the permissions that the MCP server has to access the resource/service it connects to. These permissions should be the minimum required for the MCP server to access the tool or data it is connecting to. Indirect prompt injection attacks Problem statement: Researchers have shown that the Model Context Protocol (MCP) is vulnerable to a subset of Indirect Prompt Injection attacks known as Tool Poisoning Attacks. Tool poisoning is a scenario where an attacker embeds malicious instructions within the descriptions of MCP tools. These instructions are invisible to users but can be interpreted by the AI model and its underlying systems, leading to unintended actions that could ultimately lead to harmful outcomes. Risks: Unintended AI actions present a variety of security risks that include data exfiltration and privacy breaches. Mitigating controls: Implement AI prompt shields: in Azure AI Foundry, you can follow these steps to implement AI prompt shields. Implement robust supply chain security: you can read more about how Microsoft implements supply chain security internally here. Established security best practices that will uplift your MCP implementation’s security posture Any MCP implementation inherits the existing security posture of your organization's environment that it is built upon, so when considering the security of MCP as a component of your overall AI systems it is recommended that you look at uplifting your overall existing security posture. The following established security controls are especially pertinent: Secure coding best practices in your AI application - protect against the OWASP Top 10, the OWASP Top 10 for LLMs, use of secure vaults for secrets and tokens, implementing end-to-end secure communications between all application components, etc. Server hardening – use MFA where possible, keep patching up to date, integrate the server with a third party identity provider for access, etc. Keep devices, infrastructure and applications up to date with patches Security monitoring – implementing logging and monitoring of an AI application (including the MCP client/servers) and sending those logs to a central SIEM for detection of anomalous activities Zero trust architecture – isolating components via network and identity controls in a logical manner to minimize lateral movement if an AI application were compromised. Conclusion MCP is a promising development in the AI space that enables rich data and context access. As developers embrace this new approach to integrating their organization's APIs and connectors into LLMs, they need to be aware of security risks and how to implement controls to reduce those risks. There are mitigating security controls that can be put in place to reduce the risks inherent in the current specification, but as the protocol develops expect that some of the risks will reduce or disappear entirely. We encourage you to contribute to and suggest security related MCP RFCs to make this protocol even better! With thanks to OrinThomas, dasithwijes, dendeli and Peter Marcu for their inputs and collaboration on this post.Learn more about Microsoft Security Communities.
In the last five years, Microsoft has increased the emphasis on community programs – specifically within the security, compliance, and management space. These communities fall into two categories: Public and Private (or NDA only). In this blog, we will share a breakdown of each community and how to join.Decrypt DKE protected content by Super User
In today's digital age, safeguarding sensitive information is paramount for every organization. One of the most advanced methods to ensure data security is through Double Key Encryption (DKE) protection from the Microsoft Purview solution. This encryption technique uses two keys to protect data: one key is stored securely within the organization's control, while the second key is managed by Microsoft Azure. However, decrypting DKE protected content by the organization without user interference is a complex process, especially when dealing with highly sensitive information. This is where the super user account comes into play. The super user account is a privileged account that should be configured with the necessary permissions to decrypt DKE-protected content. Setting up DKE involves several steps, including deploying the DKE service, creating sensitivity labels, and configuring client devices. Once these steps are completed, the super user account can be used to decrypt the DKE protected content, providing a secure and efficient way to manage sensitive information. Why Use a Super User Account to Decrypt DKE protected content? A super user always has the Rights Management Full Control usage right for documents protected by your organization’s Azure Information Protection tenant. This means that the super user account will have access to the first key stored in the Azure tenant. However, this alone is not sufficient to decrypt documents protected by DKE. To gain decryption access, administrators need to ensure that the super user also has access to the second key, which is stored securely within the organization. Like any other user - the super user also needs to be granted access for using the DKE key. For example, organizations can use this feature in the following scenarios: An employee leaves the organization, but highly confidential documents encrypted with DKE labels need to be accessed by directors or other VIP users. An IT administrator needs to remove the current DKE protection policy configured for files and apply a new protection policy. Administrators need to bulk decrypt files for auditing, legal, or other compliance reasons. How it works Please find the below architecture diagram which details the decryption flow of DKE. Microsoft Office client or MPIP client running under a super user account (sends the double encrypted part of the metadata that controls access (aka double encrypted content key) to Azure Information Protection Azure Information Protection checks Azure Active Directory to check access and if the user is in EntraID and configured with super user access, Azure Information Protection authorizes access and decrypts the part of the metadata controlling access using your key in Azure Information Protection. Thereby, removing the outer layer of encryption. The part of metadata controlling access to the content is now encrypted with only the DKE key Microsoft Office client or MPIP client sends the encrypted part of metadata that controls access to the content to DKE service to decrypt using customer’s private key. If this is the first time accessing the encrypted document or if cached access (End-user license) has expired, or have changed key in Azure, the DKE service will receive an empty request and will deny the access to the content from Microsoft Office client due to authentication issue. If the above happens, the DKE service sends a signal to the Microsoft Office client asking for authentication information. The Microsoft Office client sends a request to a token service in EntraID which returns the JSON web token (JWT) with adequate information to the Microsoft Office or MPIP client. The client then makes a second request to the DKE service and send the encrypted part of metadata that controls access to content (aka content key) with the JWT token it received from Azure. DKE service decrypts the encrypted part of the metadata controlling access to the content using the private key in the DKE service and sends the decrypted content key back to the client Set up Super User Account to Decrypt DKE protected content Please refer to the workflow diagram below, which outlines the configuration steps. Step 1: Configure the Super User Account in Azure RMS service using PowerShell Install AIP module by running Import-Module AIPService Connect the AIP service into your tenant by running Connect-AipService Enable the Super User feature by running Enable-AipServiceSuperUserFeature Configure the admin account into Super User Add-AipServiceSuperUser -EmailAddress <Mention the primary email address or user principal name> Validate the configuration by running Get-AipServiceSuperUser Step 2: Grant permission to Super User Account in DKE service I have added Super User account as part of Authorized Email Address in DKE service Step 3: Login as Super User Account in Office or MPIP client to decrypt the file. Try to open the DKE protected document Office application prompt for authentication Provide Super User credentials You will be able to decrypt the document Conclusion By leveraging the Super User account, organizations can ensure that they can decrypt DKE-protected documents without requiring explicit permissions on the label. This provides a secure and efficient way to manage sensitive information, especially in emergency situations where immediate access to encrypted data is necessary. Understanding and implementing this process is essential for any organization looking to enhance their data security and protect their valuable information. References The following table contains links to additional information that may provide context for the design and plan. Content Description https://learn.microsoft.com/en-us/purview/double-key-encryption Information about Double Key Encryption https://learn.microsoft.com/en-us/purview/double-key-encryption-setup Setup Double Key Encryption Service in Azure https://learn.microsoft.com/en-us/azure/information-protection/configure-super-users Configure Super User access in Azure Information ProtectionExplore how to secure AI by attending our Learn Live Series
Register to attend Learn Live: Security for AI with Microsoft Purview and Defender for Cloud starting April 15 In this month-long webinar series, IT pros and security practitioners can hone their security skillsets with a deeper understanding of AI-centric challenges, opportunities, and best practices using Microsoft Security solutions. Each session will follow a hosted demo format and cover a Microsoft Learn module (topics listed below). You can ask the SMEs questions via the chat as they show you how to use Microsoft Purview and Microsoft Defender for Cloud to protect your organization in the age of AI. Learn Live dates/topics include: April 15 at 12pm PST – Manage AI Data Security Challenges with Microsoft Purview: Microsoft Purview helps you strengthen data security in AI environments, providing tools to handle challenges from AI technology. Learn to safeguard your data and adapt to evolving security challenges in AI technology. This session will help you: Understand sensitivity labels in Microsoft 365 Copilot Secure against generative AI data exposure with endpoint Data Loss Prevention Detect generative AI usage with Insider Risk Management Dynamically protect sensitive data with Adaptive Protection April 22 at 12pm PST – Manage Compliance with Microsoft Purview with Microsoft 365 Copilot: Use Microsoft Purview for compliance management with Microsoft 365 Copilot. You'll learn how to handle compliance aspects of Copilot's AI functionalities through Purview. This session will teach you how to: Audit Copilot interactions within Microsoft 365 using Microsoft Purview Investigate Copilot interactions using Microsoft Purview eDiscovery Manage Copilot data retention with Microsoft Purview Data Lifecycle Management Monitor and mitigate risks in Copilot interactions using Microsoft Purview Communication Compliance April 29 at 12pm PST – Identify and Mitigate AI Data Security Risks: Microsoft Purview Data Security Posture Management (DSPM) for AI helps organizations monitor AI activity, enforce security policies, and prevent unauthorized data exposure. Learn how to configure DSPM for AI, track AI interactions, run data assessments, and apply security controls to reduce risks associated with AI usage. You will learn how to: Explain the purpose and benefits of Microsoft Purview DSPM for AI Set up and configure DSPM for AI to monitor AI interactions Identify and analyze AI security risks using reports and insights Run and review AI data assessments to detect oversharing risks Apply security policies, such as DLP and sensitivity labels, to protect AI-referenced data May 13 at 10am PST – Enable Advanced Protection for AI Workloads with Microsoft Defender for Cloud: As organizations use and develop AI applications, they need to address new and amplified security risks. Prepare your environment for secure AI adoption to safeguard your data and identify threats to your AI. This session will help you: Understand how Defender for Cloud can protect AI workloads Enable threat protection workloads for AI Gain application and end user context for AI alerts Register today for these new sessions. We look forward to seeing you! If you’re unable to attend a session, don’t worry—the recordings will be made available on-demand via YouTube.Introducing the Secure Future Initiative Tech Tips show!
Introducing the Secure Future Initiative: Tech Tips show! This show provides bite-sized technical tips from Microsoft security experts about how you can implement recommendations from one of the six engineering pillars of Microsoft's Secure Future Initiative in your own environment to uplift your security posture. Hosted by Sarah Young, Principal Security Advocate (_@sarahyo) and Michael Howard, Senior Director Microsoft Red Team (@michael_howard), the series interviews a range of Microsoft security experts giving you practical advice about how to implement SFI controls in your organization's environment. The first episode about phishing resistant creds is live on YouTube and MS Learn. Upcoming episodes include: Using managed identities Using secure vaults to store secrets Applying ingress and egress control Scanning for creds in code and push protection Enabling audit logs for cloud and develop threat detections Keep up to date with the latest Secure Future Initiative news at aka.ms/sfi
