HomeLibrechatCVE-2026-31951

CVE-2026-31951

MEDIUM
6.8CVSS
Published: 2026-03-27
Updated: 2026-03-30
AI Analysis

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 Metrics

Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
Attack Vector
network
Complexity
low
Privileges
low
User Action
required
Scope
changed
Confidentiality
high
Integrity
none
Availability
none
Weaknesses
CWE-200

Metadata

Primary Vendor
LIBRECHAT
Published
3/27/2026
Last Modified
3/30/2026
Source
NIST NVD
Note: Verify all details with official vendor sources before applying patches.

Affected Products

librechat : librechatlibrechat : librechat

AI-Powered Remediation

Generate remediation guidance or a C-suite brief for this vulnerability.

Executive Intelligence Brief

CVE-CVE-2026-31951 | MEDIUM Severity | CVEDatabase.com | CVEDatabase.com