Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
danny-avila LibreChat
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

LibreChat是LibreChat开源的一个免费、高度可定制的统一 AI 对话平台，能够在一个界面中聚合并运行来自任意厂商的大模型。 LibreChat 0.8.2-rc1至0.8.3-rc1版本存在信息泄露漏洞，该漏洞源于用户创建的MCP服务器可包含经过凭据占位符替换的任意HTTP标头，可能导致攻击者创建包含特定令牌的恶意MCP服务器，致使调用该服务器上工具的受害者OAuth令牌被窃取。

CVSS 6.8 · Medium EPSS 0.35% · P27

Possible ATT&CK Techniques 1 AI

T1530 · Data from Cloud Storage
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-31951

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
LibreChat's MCP Server Header Injection Enables OAuth Token Theft
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
信息暴露
Source: CVE Program / CVE List V5
Vulnerability Title
LibreChat 信息泄露漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
LibreChat是LibreChat开源的一个免费、高度可定制的统一 AI 对话平台，能够在一个界面中聚合并运行来自任意厂商的大模型。 LibreChat 0.8.2-rc1至0.8.3-rc1版本存在信息泄露漏洞，该漏洞源于用户创建的MCP服务器可包含经过凭据占位符替换的任意HTTP标头，可能导致攻击者创建包含特定令牌的恶意MCP服务器，致使调用该服务器上工具的受害者OAuth令牌被窃取。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
danny-avila LibreChat >= v0.8.2-rc1, <= v0.8.3-rc1 -

II. Public POCs for CVE-2026-31951

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-31951

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-31951 (1)

Same Patch Batch · danny-avila · 2026-03-27 · 4 CVEs total

CVE-2026-31943 8.5 HIGH LibreChat has SSRF protection bypass via IPv4-mapped IPv6 normalization in isPrivateIP
CVE-2026-31945 7.7 HIGH LibreChat Server-Side Request Forgery using DNS resolution
CVE-2026-31950 5.3 MEDIUM LibreChat's IDOR in SSE Stream Subscription Allows Reading Other Users' Chats

IV. Related Vulnerabilities

Same product: LibreChat
Same vendor: danny-avila
Same weakness: CWE-200

V. Comments for CVE-2026-31951

No comments yet

Leave a comment