CVE-2026-31951
March 27, 2026
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.
Affected Packages
https://github.com/danny-avila/LibreChat.git (GITHUB):
Affected version(s) >=v0.0.1 <v0.8.3-rc2Fix Suggestion:
Update to version v0.8.3-rc2https://github.com/danny-avila/LibreChat.git (GITHUB):
Affected version(s) >=v0.0.1 <v0.8.3-rc2Fix Suggestion:
Update to version v0.8.3-rc2https://github.com/danny-avila/LibreChat.git (GITHUB):
Affected version(s) >=v0.0.1 <v0.8.3-rc2Fix Suggestion:
Update to version v0.8.3-rc2Related Resources (1)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.2
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
PASSIVE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
NONE
Vulnerable System Availability
NONE
Subsequent System Confidentiality
HIGH
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
6.8
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
REQUIRED
Scope
CHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
NONE
Weakness Type (CWE)
Exposure of Sensitive Information to an Unauthorized Actor
