CVE-2026-31951
MEDIUM EPSS 15.4%
Published Mar 27, 20263mo ago · Modified Jun 17, 20261w ago
5.7 CVSS 3.1
Published Mar 27, 2026 3mo ago
Last Modified Jun 17, 2026 1w ago
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 Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N Attack Vector Network
Attack Complexity Low
Privileges Required Low
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity None
Availability None
Threat Intelligence
EPSS Exploit Probability
15.4% percentile
Exploit & Patch Status
Public Exploit Known
No Patch Available
Weaknesses 1
CWE-200 Exposure of Sensitive Information to an Unauthorized Actor Information Exposure
Affected Products 2
References 1
- github.com https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.