Vulnerability Description
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Librechat | Librechat | >= 0.8.2, < 0.8.3 |
Related Weaknesses (CWE)
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954ExploitVendor Advisory
FAQ
What is CVE-2026-31951?
CVE-2026-31951 is a vulnerability with a CVSS score of 6.8 (MEDIUM). LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo creden...
How severe is CVE-2026-31951?
CVE-2026-31951 has been rated MEDIUM with a CVSS base score of 6.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-31951?
Check the references section above for vendor advisories and patch information. Affected products include: Librechat Librechat.