CVE-2026-32625: LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
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 CREDSKEY, CREDSIV, JWTSECRET, and MONGOURI 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 Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
LibreChat (MCP server integration)to a version that resolves this vulnerability.Fixed in 0.8.4-rc1
Event History
Frequently Asked Questions
What is the severity of CVE-2026-32625?
The severity of CVE-2026-32625 is critical with a score of 9.6.
What vulnerability does CVE-2026-32625 describe?
CVE-2026-32625 describes a vulnerability in LibreChat that allows exfiltration of server secrets via MCP server URL injection.
How do I fix CVE-2026-32625?
To fix CVE-2026-32625, upgrade LibreChat to version 0.8.4 or later where the issue is resolved.
What are the potential impacts of CVE-2026-32625?
CVE-2026-32625 can lead to sensitive information leakage, compromising server authentication secrets.
Which versions of LibreChat are affected by CVE-2026-32625?
CVE-2026-32625 affects all versions of LibreChat up to and including version 0.8.3.