CVE-2026-32625 LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: no · technical impact: total
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.
Upgrade path
2 packages: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| LibreChat | < 0.8.4 | 0.8.4 | Fixed |
| danny-avila LibreChat | = < 0.8.4-rc1 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| danny-avila LibreChat | = < 0.8.4-rc1 | No fix listed |
| LibreChat | < 0.8.4 | 0.8.4 |
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx exploit mitigation vendor-advisory