Vulnerability · Published Jun 2, 2026 · Assigned by GitHub_M
CVE-2026-32625LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
Critical 9.6
In plain English
A critical-severity information exposure in LibreChat from danny-avila. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 2.8% (higher than 86% of all known vulnerabilities).
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| danny-avila | LibreChat | < 0.8.4-rc1 |
Weakness: CWE-200 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx x_refsource_CONFIRM