AI Security
Lessons from the field. Always landing on my feet.
Agent 365 Ships May 1. I Tested the Defender Playbook for AI Agent Attacks.
Microsoft Agent 365 goes generally available on May 1, 2026. Most launch-week posts will explain what it is. I wanted to answer a different question: What does an AI agent attack look like in a real Microsoft defender stack before Agent 365 becomes …
Block Prompt Injection at the Network Layer with Entra Prompt Shield
A while back I built an LLM Firewall with AWS Lambda, a proxy that sits between users and the model to catch prompt injection. It worked, but it meant writing custom code for every app and having zero visibility into AI services I didn’t own. That’s …
Just-In-Time Access for AI Agents: Building a ZSP Gateway in Azure
AI coding assistants need Contributor access to deploy infrastructure. Backup automation needs Key Vault secrets at 2 AM. Security scanners need Reader access on a schedule. The easy answer is standing permissions-give each service principal what it …
Building an LLM Prompt Injection Firewall with AWS Lambda
AWS continues to enhance its generative AI security capabilities, with improved prompt attack filtering now available in Amazon Bedrock Guardrails. Despite these advances, a significant gap remains: organizations are deploying LLM capabilities faster …
Sentinel MCP Server: Securing Your SOC's New AI Attack Surface
In September 2025, Microsoft announced the Sentinel MCP Server, a Model Context Protocol implementation that lets MCP-compatible AI assistants query your Sentinel data using natural language. Microsoft highlights GitHub Copilot, Copilot Studio, and …
Securing the Agentic Workforce: Microsoft's Zero Trust for AI Agents
The enterprise is entering uncharted territory. AI agents, autonomous systems that can browse the web, execute code, access databases, and interact with third-party services, are no longer experimental. They’re being deployed at scale. And they’re …