CVE-2026-31951

EUVD-2026-16769
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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTPrimary
6.8 MEDIUM
NETWORK
LOW
LOW
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
Base Score
CVSS 3.x
EPSS Score
Percentile: 11%
Affected Products (NVD)
VendorProductVersion
librechatlibrechat
0.8.2 ≤
𝑥
< 0.8.3
librechatlibrechat
0.8.3:rc1
𝑥
= Vulnerable software versions
Common Weakness Enumeration
References
https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954