Nixpkgs Security Tracker

Login with GitHub

Details of issue NIXPKGS-2026-0845

NIXPKGS-2026-0845
published on 31 Mar 2026
Permalink CVE-2026-31951
6.8 MEDIUM
  • CVSS version: 3.1
  • Attack vector (AV): NETWORK
  • Attack complexity (AC): LOW
  • Privileges required (PR): LOW
  • User interaction (UI): REQUIRED
  • Scope (S): CHANGED
  • Confidentiality impact (C): HIGH
  • Integrity impact (I): NONE
  • Availability impact (A): NONE
updated 11 hours ago by @mweinelt Activity log
  • Created automatic suggestion 3 days, 19 hours ago
  • @mweinelt accepted 11 hours ago
  • @mweinelt published on GitHub 11 hours ago
LibreChat's MCP Server Header Injection Enables OAuth Token Theft

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.

References

Affected products

LibreChat
  • ==>= v0.8.2-rc1, <= v0.8.3-rc1

Matching in nixpkgs

pkgs.librechat

Open-source app for all your AI conversations, fully customizable and compatible with any AI provider

Package maintainers

https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954