The NAS Digital Blog

Practical security guidance, .NET deep-dives, and the occasional rabbit hole — written for the engineers shipping AI into systems that matter.

Security Semantic Kernel CVE MCP

There's a Second, Worse Semantic Kernel CVE, and It's Part of a Pattern

A few months ago I wrote about CVE-2026-25592, the CVSS 9.9 prompt injection bug in Microsoft's Semantic Kernel that let a malicious prompt reach code execution. At the time I treated it as a single, severe, but isolated incident.

It wasn't isolated. Microsoft has now disclosed CVE-2026-26030, a second Semantic Kernel vulnerability, CVSS 9.9. And the pattern it's part of is bigger than one framework.

Read full article
Security Semantic Kernel SQL Injection .NET Azure AI Agents NL2SQL

Your Semantic Kernel Text-to-SQL Agent Trusts the LLM. That's the Vulnerability.

I last wrote about CVE-2026-25592, a CVSS 9.9 vulnerability in Semantic Kernel's DownloadFileAsync helper. The fix was a one-line patch. The argument I made was that the patch closes the specific exploit but does nothing about the architectural mistake underneath: treating [KernelFunction] as documentation rather than as a security boundary.

That post focused on file paths. This one is about something more common and, in production, far more damaging.

Read full article
Security Semantic Kernel CVE .NET Azure AI Agents

Your Semantic Kernel Agent May Still Be Vulnerable After the CVSS 9.9 Fix

On 7 May 2026, Microsoft disclosed critical vulnerabilities in Semantic Kernel, the official .NET framework used to build AI agents and LLM-powered applications. Among them was CVE-2026-25592, a vulnerability that received a CVSS 9.9 rating.

If you've upgraded to Semantic Kernel 1.71.0, you've applied Microsoft's official fix. Many teams considered the issue closed at that point.

Read full article