CVE-2026-31951

Source
https://cve.org/CVERecord?id=CVE-2026-31951
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-31951.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-31951
Aliases
  • GHSA-pmw7-gqwj-f954
Published
2026-03-27T19:29:25.892Z
Modified
2026-04-02T13:26:34.599001Z
Severity
  • 6.8 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N CVSS Calculator
Summary
LibreChat's MCP Server Header Injection Enables OAuth Token Theft
Details

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.

Database specific
{
    "cwe_ids": [
        "CWE-200"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/31xxx/CVE-2026-31951.json",
    "cna_assigner": "GitHub_M"
}
References

Affected packages

Git / github.com/danny-avila/librechat

Affected ranges

Type
GIT
Repo
https://github.com/danny-avila/librechat
Events
Database specific
{
    "versions": [
        {
            "introduced": "v0.8.2-rc1"
        },
        {
            "last_affected": "v0.8.3-rc1"
        }
    ]
}

Affected versions

chart-1.*
chart-1.9.5
chart-1.9.6
chart-1.9.7
chart-1.9.8
v0.*
v0.8.2
v0.8.2-rc1
v0.8.2-rc2
v0.8.2-rc3
v0.8.3-rc1

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-31951.json"