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.