CVE-2026-32625

Published: Giu 03, 2026 Last Modified: Giu 03, 2026
ExploitDB:
Other exploit source:
Google Dorks:
CRITICAL 9,6
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Scope: changed
Confidentiality: high
Integrity: high
Availability: none

Description

AI Translation Available

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.

200

Exposure of Sensitive Information to an Unauthorized Actor

Draft
Abstraction: Class Structure: Simple
Common Consequences
Security Scopes Affected:
Confidentiality
Potential Impacts:
Read Application Data
Applicable Platforms
Technologies: Not Technology-Specific, Web Based, Mobile
Likelihood of Exploit: High
View CWE Details
https://github.com/danny-avila/LibreChat/security/advisorie…
https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx