CVE-2026-32625
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…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (2.94%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 9.6 CRITICALCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N
- EPSS
- 2.94% probability · 86th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-200
- Affected
- librechat/librechat
- Source
- security-advisories@github.com
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwxExploit, Mitigation, Vendor Advisory
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwxExploit, Mitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.