Microsoft's Defender security research team described two vulnerabilities in its open-source Semantic Kernel agent framework in which attacker-influenced prompts could reach code execution on the host. One involved unsafe string interpolation in an in-memory vector store filter; the other exposed a code-execution plugin function that allowed arbitrary file writes outside its sandbox. Both were fixed in updated SDK releases.
Why it matters
Shows that agent framework plumbing, not just the model, can turn a prompt injection into host compromise.
Key facts
As stated in the sources, with where to find them.
- CVE-2026-26030 affects the Semantic Kernel Python SDK before 1.39.4 (in-memory vector store).Vulnerability sections
- CVE-2026-25592 affects the .NET SDK before 1.71.0 (SessionsPythonPlugin), enabling file writes to the host filesystem.Vulnerability sections
Findings that cite this record
Key questions this bears on
- Can prompt injection against AI agents be reliably defended?Not reliably. Bounding what untrusted input can trigger helps, but trust boundaries must survive delegation and tool execution.
- Where are deployed AI agents actually being exploited?Exploitation often reaches deployed agents through connectors, credentials, tools and packages.
- Do cyber evaluations of AI agents stay contained?Not reliably. Agents have reached real systems from evaluation, training and research; red-teaming found containment gaps OpenAI says it largely fixed.
Sources
Related records
Oct 29, 2026
Oct 13, 2026
Jul 1, 2026
Aug 1, 2025
Sep 30, 2026
Apr 15, 2026