Servers and applications
GHSA-889f-5j9v-j8p3
MCP editor can send an owner's preserved API key to a replacement endpoint
- Severity
- High 7.7
- Published
- 17 Nov 2026
- Last changed
- 17 Nov 2026
- Added to UpHeron
- 17 Nov 2026
- Fixed in
- 0.8.8
- Attack
- Over the network · Needs a user account · No user action needed
- Attacker can
- Read data
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N- Sources
- Project advisories (GitHub)
Description
An ordinary user with the documented Editor role on another user's shared MCP server can redirect that server to an attacker-controlled URL and make LibreChat send the owner's hidden API key to it.
The API correctly redacts apiKey.key from the Editor. However, when the Editor changes the URL and submits the redacted API-key object without key, LibreChat retrieves the owner's decrypted key, combines it with the Editor's URL, and immediately connects during update inspection. The attacker's receiver obtains the complete reusable key before the PATCH returns. The victim does not need to interact.
This is runtime-confirmed on the latest published release, v0.8.8-rc3, using the official image, real JWTs, two ordinary users, Mongo ACLs, encrypted credential storage, the production MCP inspector, and actual outbound HTTP capture.
- MCP creation and sharing are enabled.
- Victim user A owns a shared MCP server with an admin-sourced Bearer, Basic, or custom-header API key.
Affected software
| Software | Affected versions |
|---|---|
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
- GitHub Advisory Database https://github.com/advisories/GHSA-889f-5j9v-j8p3
- github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-889f-5j9v-j8p3