CVE-2026-32625

LibreChat Exfiltrates Server Secrets via MCP Server URL Injection

State: Published
Severity: 9.6 Critical
Published: Jun 2, 2026
Updated: Jun 3, 2026
Reserved: Mar 12, 2026

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.

Scores

CVSS	Score	Vector	Source
3.1	9.6 Critical	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N	GitHub_M

Weaknesses

CWE-200 Exposure of Sensitive Information to an Unauthorized Actor

Affected Products

Product	Versions
LibreChatdanny-avila	< 0.8.4-rc1Affected

References

https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.