CVE-2026-26030
Microsoft Semantic Kernel InMemoryVectorStore filter functionality vulnerable to remote code execution
Description
Semantic Kernel, Microsoft's semantic kernel Python SDK, has a remote code execution vulnerability in versions prior to 1.39.4, specifically within the `InMemoryVectorStore` filter functionality. The problem has been fixed in version `python-1.39.4`. Users should upgrade this version or higher. As a workaround, avoid using `InMemoryVectorStore` for production scenarios.
INFO
Published Date :
Feb. 19, 2026, 5:24 p.m.
Last Modified :
June 17, 2026, 10:25 a.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | CRITICAL | [email protected] |
Solution
- Upgrade Semantic Kernel to version 1.39.4 or higher.
- Avoid using InMemoryVectorStore in production.
Public PoC/Exploit Available at Github
CVE-2026-26030 has a 17 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-26030.
| URL | Resource |
|---|---|
| https://github.com/microsoft/semantic-kernel/pull/13505 | Issue Tracking Patch |
| https://github.com/microsoft/semantic-kernel/releases/tag/python-1.39.4 | Release Notes |
| https://github.com/microsoft/semantic-kernel/security/advisories/GHSA-xjw9-4gw8-4rqx | Patch Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-26030 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-26030
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Provable, injection-resistant action limits for autonomous LLM agents
Python TeX
252 standalone, live-validated CVE exploit PoCs (pure-Python stdlib) across web apps, AI/ML platforms and the Linux kernel; 75 in the CISA KEV catalog. For authorized security testing and education.
cve exploit penetration-testing poc security-research vulnerability cybersecurity ethical-hacking infosec rce red-team security appsec cisa-kev deserialization exploit-development proof-of-concept python
Python C
Ethical, network-isolated Docker lab reproducing CVE-2026-26030 — Semantic Kernel in-memory vector store filter eval() RCE (patched in 1.39.4)
Python Shell HTML
A lightweight, zero-dependency Local Agentic Virtual Machine enforcing deterministic Cognitive-Executive Separation for autonomous AI workflows.
Python
None
None
Python
Profile README
Curadoria viva de projetos e insights sobre AI agents, multi-agent systems, e infra de produção. Atualizado automaticamente pelo Growth Agent.
A curated list of attack classes and its defenses when building a production grade agents workflow for organizational data.
Deterministic, zero-dependency Python firewall for AI agents — MCP rug-pull, memory poisoning, indirect injection, exfil channels. 44 compliance templates (US/CN/JP/EU).
ai-security firewall llm mcp owasp prompt-injection ai-agent compliance cybersecurity guardrails jailbreak-detection open-source python
Makefile Python Dockerfile Mako HTML Shell TypeScript JavaScript CSS
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
ai-agent-security ai-agents ai-security awesome-list cybersecurity llm-security mcp-security prompt-injection supply-chain-security adversarial-attacks agent-security agentic-ai ai-attacks ai-safety cve incident-response owasp red-team security-research vulnerability
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. 768 rules across 10 categories; merged into Microsoft AGT, Cisco AI Defense, MISP, OWASP A-S-R-H, FINOS & SigmaHQ. MIT-licensed.
agent-security ai-security llm-security mcp-security owasp prompt-injection sigma-rules threat-detection garak owasp-agentic agent-threat-rules
TypeScript JavaScript Python Shell CSS HTML Dockerfile
None
A deny-by-default contract & type-checker layer for AI agent tool calls — Pydantic-based, in-process, zero-core-deps. Validates the actual tool-call payload (ghost-arg stripping, strict types, self-healing retries) beneath MCP gateways & firewalls. Works with LangChain, OpenAI Agents SDK, PydanticAI & CrewAI.
ai-agents ai-security crewai firewall langchain llm-safety mcp-server openai pii-masking pydantic-ai python rbac sandbox tool-validation zero-trust
Python Makefile JavaScript HTML CSS Dockerfile
caro: fast Rust CLI that turns natural‑language tasks into a safe POSIX command. Built for macOS (MLX/Metal) with a built‑in model; supports vLLM/Ollama/LM Studio. JSON‑only output, safety checks, confirmation, multi‑step goals, devcontainer included.
ai cmd command-line devops posix runbook unix rust local-llm
Shell PowerShell Makefile Rust RenderScript Python JavaScript HTML Astro Dockerfile
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-26030 vulnerability anywhere in the article.
-
The Hacker News
Open-Source Android AI Agents Could Let Invisible Screen Text Run Code on Host PCs
An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same a ... Read more
-
The Hacker News
AutoJack Attack Lets One Web Page Hijack AI Agent for Host Code Execution
Microsoft researchers have detailed an exploit chain, named AutoJack, that turns an AI browsing agent into a delivery vehicle for remote code execution. Steer the agent to load an attacker's web page, ... Read more
The following table lists the changes that have been made to the
CVE-2026-26030 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'microsoft', 'product': 'semantic-kernel', 'versions': [{'status': 'affected', 'version': '< 1.39.4'}]}] -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-26030', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-02-20T04:55:50.393336Z'} -
Initial Analysis by [email protected]
Mar. 03, 2026
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:microsoft:semantic_kernel:*:*:*:*:*:python:*:* versions up to (excluding) 1.39.4 Added Reference Type GitHub, Inc.: https://github.com/microsoft/semantic-kernel/pull/13505 Types: Issue Tracking, Patch Added Reference Type GitHub, Inc.: https://github.com/microsoft/semantic-kernel/releases/tag/python-1.39.4 Types: Release Notes Added Reference Type GitHub, Inc.: https://github.com/microsoft/semantic-kernel/security/advisories/GHSA-xjw9-4gw8-4rqx Types: Patch, Vendor Advisory -
New CVE Received by [email protected]
Feb. 19, 2026
Action Type Old Value New Value Added Description Semantic Kernel, Microsoft's semantic kernel Python SDK, has a remote code execution vulnerability in versions prior to 1.39.4, specifically within the `InMemoryVectorStore` filter functionality. The problem has been fixed in version `python-1.39.4`. Users should upgrade this version or higher. As a workaround, avoid using `InMemoryVectorStore` for production scenarios. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H Added CWE CWE-94 Added Reference https://github.com/microsoft/semantic-kernel/pull/13505 Added Reference https://github.com/microsoft/semantic-kernel/releases/tag/python-1.39.4 Added Reference https://github.com/microsoft/semantic-kernel/security/advisories/GHSA-xjw9-4gw8-4rqx