All vulnerabilities

Servers and applications

CVE-2026-22252

LibreChat MCP Stdio Remote Command Execution

Severity
Critical 9.9
Published
10 Jan 2026
Last changed
17 Jun 2026
Added to UpHeron
1 Nov 2026
Exploit chance
4.2% in the next 30 daysHigher than 91% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Improper authorization (CWE-285)
Attack
Over the network · Needs a user account · No user action needed
Attacker can
Read data · Change data · Take it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Also known as
GHSA-cxhj-j78r-p88f
Sources
NVD, Project advisories (GitHub)

Description

LibreChat's MCP stdio transport accepts arbitrary commands without validation, allowing any authenticated user to execute shell commands as root inside the container through a single API request.

LibreChat's MCP (Model Context Protocol) implementation allows authenticated remote code execution as root. By registering an account and sending a single HTTP request to the API, anyone can execute arbitrary shell commands as the root user inside the container. This vulnerability works on the default installation.

Three factors combine to create this vulnerability:

  • Insecure Default Permissions - MCP server creation is enabled for all users by default
  • No Input Validation - The stdio command field accepts arbitrary shell commands
  • Immediate Execution - Commands run when the MCP server is created during "inspection"

This is an Authenticated Remote Code Execution (RCE) vulnerability. Any user who can register an account on a vulnerable LibreChat instance can execute arbitrary commands…

From LibreChat-AI/LibreChat's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
LibreChatServers and applications · cpe:a:librechat:librechat
  • Version 0.8.2-rc1
LibreChatServers and applications · github:librechat-ai/librechat
  • Version 0.8.2-rc1

About LibreChat

Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active

From its GitHub repository.
Docker Hub pulls
669,094Docker Hub, 15 Nov 2026
GitHub stars
47,138GitHub, 15 Nov 2026
Forks
9,706GitHub, 15 Nov 2026
License
MITGitHub
First published on GitHub
12 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-22252
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-22252
  • GitHub Advisory Database https://github.com/advisories/GHSA-cxhj-j78r-p88f
  • github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-cxhj-j78r-p88f