CVE-2026-32625
LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
Description
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.
INFO
Published Date :
June 2, 2026, 11:16 p.m.
Last Modified :
July 22, 2026, 7:10 p.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
- Update LibreChat to version 0.8.4-rc1 or later.
- Apply the security patch provided by the vendor.
Public PoC/Exploit Available at Github
CVE-2026-32625 has a 3 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-2026-32625.
| URL | Resource |
|---|---|
| https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx | Exploit Mitigation Vendor Advisory |
| https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx | Exploit Mitigation 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-2026-32625 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-2026-32625
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).
The Project shares all information on MCP related CVE's published
mcp mcp-security mcp-cve
Static scanner for MCP-connected AI agent pipelines — 225 rules across 11 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.
ai-agent ai-security claude-code github-action mcp mcp-security owasp sarif scanner security supply-chain-security tool-poisoning ai-agent-security ai-safety security-scanner static-analysis
Python Dockerfile Shell TypeScript HTML Makefile
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
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-32625 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-32625 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 Translated by [email protected]
Jul. 22, 2026
Action Type Old Value New Value Added Translation Title: LibreChat de danny-avila, Description: LibreChat es un clon mejorado de ChatGPT que soporta múltiples proveedores de IA. En versiones hasta la 0.8.3 inclusive, la integración del servidor del Protocolo de Contexto del Modelo (MCP) resuelve los marcadores de posición ${VAR} contra el process.env del servidor durante la validación del esquema Zod de las URL de servidor MCP proporcionadas por el usuario. Cualquier usuario autenticado puede crear una configuración de servidor MCP maliciosa con una URL que apunte a un dominio controlado por un atacante que contenga referencias a variables de entorno, lo que hace que el servidor de LibreChat se conecte al servidor del atacante y transmita secretos críticos como CREDS_KEY, CREDS_IV, JWT_SECRET y MONGO_URI en la URL de la solicitud. Esto permite el compromiso total de los materiales criptográficos de la instalación y las credenciales de la base de datos sin requerir privilegios administrativos. Esto está parcheado en la versión 0.8.4-rc1. -
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'danny-avila', 'product': 'LibreChat', 'versions': [{'status': 'affected', 'version': '< 0.8.4-rc1'}]}] -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-32625', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-06-03T13:28:03.174610Z'} -
Initial Analysis by [email protected]
Jun. 04, 2026
Action Type Old Value New Value Added CWE NVD-CWE-noinfo Added CPE Configuration OR *cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:* versions up to (excluding) 0.8.4 Added Reference Type CISA-ADP: https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx Types: Exploit, Mitigation, Vendor Advisory Added Reference Type GitHub, Inc.: https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx Types: Exploit, Mitigation, Vendor Advisory -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 03, 2026
Action Type Old Value New Value Added Reference https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx -
New CVE Received by [email protected]
Jun. 02, 2026
Action Type Old Value New Value Added Description LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N Added CWE CWE-200 Added Reference https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx