Servers and applications
GHSA-qjp6-mg6p-xvqq
MCP OAuth client_secret exfiltration — a shared-server editor can redirect the confidential secret to an attacker-controlled token endpoint
- Severity
- Medium 4.9
- 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 an administrator account · No user action needed
- Attacker can
- Read data
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:N/A:N- Sources
- Project advisories (GitHub)
Description
A user who is granted edit access to a shared, database-stored MCP server that uses a manually-configured OAuth client (oauth.client_id + oauth.client_secret + oauth.authorization_url + oauth.token_url, without OBO) can steal that server's confidential oauth.client_secret — a value they are not allowed to read — by updating oauth.token_url to point at a server they control and omitting client_secret from the update. The backend preserves the owner's stored secret and, on the next OAuth exchange/refresh for that server, sends it (via client_secret_basic/client_secret_post) to the attacker-controlled token endpoint.
This bypasses the response-time redaction that hides oauth.client_secret from viewers/editors: the secret cannot be read over the API, but it can be redirected to the attacker through a configuration change.
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-qjp6-mg6p-xvqq
- github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-qjp6-mg6p-xvqq