CVE-2026-32625
- Source
- https://cve.org/CVERecord?id=CVE-2026-32625
- Import Source
- https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-32625.json
- JSON Data
- https://api.osv.dev/v1/vulns/CVE-2026-32625
- Aliases
-
- GHSA-4pcc-j6m6-wcwx
- Published
- 2026-06-02T22:35:00.859Z
- Modified
- 2026-07-08T08:13:03.291685Z
- Severity
-
- 9.6 (Critical) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N CVSS Calculator
- Summary
- LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
- Details
-
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.
- Database specific
{ "cna_assigner": "GitHub_M", "cwe_ids": [ "CWE-200" ], "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/32xxx/CVE-2026-32625.json" }- References
Affected packages
Git / github.com/danny-avila/librechat
Affected ranges
- Type
- GIT
- Repo
- https://github.com/danny-avila/librechat
- Events
-
Introduced0 Unknown introduced commit / All previous commits are affectedFixed
- Database specific
{ "extracted_events": [ { "introduced": "0" }, { "fixed": "0.8.4-rc1" }, { "fixed": "0.8.4" } ], "cpe": "cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:*", "source": [ "AFFECTED_FIELD", "CPE_RANGE" ] }