CVE-2026-32625 LibreChat Exfiltrates Server Secrets via MCP Server URL Injection

Critical 9.6 Published 2 Jun 2026 Updated 3 Jun 2026

Authenticated users can exfiltrate server secrets like JWT keys and database credentials by injecting environment variable references into MCP server URLs.

Exploited in the wild: Not known
Login needed: Any signed-in user
Attackable: Over the internet
Victim action needed: Not needed
Fix: None listed

What is CVE-2026-32625?

CVE-2026-32625 is a critical vulnerability in Librechat Librechat, published on 2 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim.

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.

Weakness: CWE-200

Which versions are affected by CVE-2026-32625?

It affects 1 product.

Products include Librechat Librechat.

How do I fix CVE-2026-32625?

No fix has been published for CVE-2026-32625 yet. Limit exposure of the affected software until one is available.

Is CVE-2026-32625 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-32625 exists.

All Librechat Librechat vulnerabilities

Sources

Also known as GHSA-4pcc-j6m6-wcwx.