The knowledge base

Security knowledge.
Organized around the work.

Move from a product question to a control you can investigate. Explore a topic, follow a learning path, or search the full collection.

30 guides25 security topicsBrowse all topics

30 guides

2 guides

Security foundations

Map the system, establish the boundaries, and collect evidence that controls work.

Explore topic
Foundations4 min read

Build your Microsoft AI security baseline

Build an evidence-based baseline for Microsoft AI: identify the workload, constrain data and actions, test boundaries, and prepare incident response.

Documentation checked

3 guides

Microsoft 365 Copilot

Control oversharing, understand protection boundaries, and investigate organizational data use.

Explore topic
Microsoft 365 Copilot4 min read

Run a Copilot oversharing remediation campaign

Prioritize exposed SharePoint content, assign accountable owners, remove unnecessary permissions, and verify access before closing findings.

Documentation checked
Microsoft 365 Copilot4 min read

Review Copilot data boundaries before rollout

Separate Copilot permissions, discovery restrictions, encryption and DLP, then verify what users can retrieve, summarize and share.

Documentation checked

6 guides

Azure AI & Foundry

Design identity, networking, secrets and policy around the AI workload you actually run.

Explore topic
Azure AI4 min read

Build a prompt-injection defense test plan

Combine Prompt Shields with deterministic authorization, controlled tool execution, and repeatable tests of retrieved content and tool responses.

Documentation checked
Azure AI4 min read

Verify Azure AI network isolation end to end

Separate private inbound access, DNS, outbound dependencies, and identity checks before calling a Foundry deployment network-isolated.

Documentation checked

4 guides

Agents & Copilot Studio

Constrain connectors, tool authority and the consequential actions an agent can take.

Explore topic
Agents4 min read

Govern agent connectors before they move data

Turn a Copilot Studio connector inventory into scoped data policies, verified endpoint controls, and accountable changes across environments.

Documentation checked
Agents7 min read
Advanced guide

Engineer MCP tool trust boundaries beyond the prompt

Design per-request authorization, tool admission, downstream identity and consequential-action approval for remote MCP integrations with Microsoft Foundry.

Documentation checked

5 guides

Detection & response

Build useful telemetry, investigate competing explanations, and contain the relevant authority.

Explore topic
Detection & response5 min read
Advanced guide

Validate Sentinel detections beyond a successful KQL parse

Test schema assumptions, event semantics, ingestion timing, join behavior, scheduling, entity mapping, and analyst outcomes before promoting a hunt into a detection.

Documentation checked

2 guides

Governance & assurance

Make release decisions with named owners, reproducible evidence and explicit exceptions.

Explore topic
Governance4 min read

Use an evidence-based AI release checklist

Tie each release to its identities, tools, data sources, test evidence, deployment settings, and recovery decision before expanding access.

Documentation checked

4 guides

Identity & authorization

Trace delegated authority, token audiences, privileged access and federation trust.

Explore topic
Identity & authorization5 min read
Advanced guide

Design Conditional Access around AI identity types

Separate human, service-principal, managed-identity, and preview agent policy boundaries; validate token acquisition and resource enforcement independently.

Documentation checked
Identity & authorization7 min read
Advanced guide

Design delegated authorization across an agent tool chain

Separate user delegation from application authority, validate token boundaries, and prevent an agent from turning an authorized session into an unauthorized action.

Documentation checked
Identity & authorization5 min read
Advanced guide

Constrain privileged access across the AI control plane

Design PIM activation, resource scope, approval evidence, and emergency recovery around the permissions that can change models, data, identities, and telemetry.

Documentation checked

3 guides

Retrieval & data security

Protect document permissions, ingestion integrity and the storage behind AI grounding.

Explore topic
Retrieval & data security5 min read
Advanced guide

Secure the storage data plane behind AI retrieval

Separate ingestion and serving authority, close Shared Key and anonymous paths, constrain SAS use, and validate Blob and Data Lake access independently.

Documentation checked
Retrieval & data security7 min read
Advanced guide

Enforce document authorization before RAG grounding

Choose between application security filters and native preview permissions, preserve access metadata on chunks, and enforce the same boundary across keyword and vector retrieval.

Documentation checked
Retrieval & data security7 min read
Advanced guide

Protect RAG ingestion against poisoned and untraceable content

Separate source access from content trust, preserve provenance through chunking, and verify publication, deletion, and rollback without assuming a prompt filter proves integrity.

Documentation checked

1 guide

Adversarial testing

Design threat-led experiments, inspect real side effects and interpret evaluation limits.

Explore topic