UTC
Critical

Semantic Kernel has Arbitrary File Write via AI Agent Function Calling in .NET SDK

CVE-2026-25592 · GHSA-2ww3-72rp-wpp4 · published 2026-02-06 · updated 2026-02-20

Severity
Critical
CVSS score
9.9
Chance of exploitation (EPSS)
2.5%
Fixed in
1.71.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

What kind of vulnerability is it? Who is impacted? An Arbitrary File Write vulnerability has been identified in Microsoft's Semantic Kernel .NET SDK, specifically within the SessionsPythonPlugin. Developers who have built applications which include Microsoft's Semantic Kernel .NET SDK and are using the SessionsPythonPlugin

What to do

Upgrade Microsoft.SemanticKernel.Core to 1.71.0 or later, and semantic-kernel to 1.39.3 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Has the problem been patched? What versions should users upgrade to? The problem has been fixed in Microsoft.SemanticKernel.Plugins.Core version 1.71.0. Users should upgrade to version 1.71.0 or higher.

If you cannot upgrade yet

Is there a way for users to fix or remediate the vulnerability without upgrading? Users can create a Function Invocation Filter which checks the arguments being passed to any calls to DownloadFileAsync or UploadFileAsync and ensures the provided localFilePath is allow listed.

Affected
PackageRegistryAffectedFixed in
Microsoft.SemanticKernel.CoreNuGet< 1.71.01.71.0
semantic-kernelPyPI< 1.39.31.39.3
Also in Microsoft.SemanticKernel.Core, semantic-kernel
  1. CriticalMicrosoft Semantic Kernel InMemoryVectorStore filter functionality vulnerable to remote code executionsemantic-kernel

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].