CVE-2026-44653
Last modified
CVE-2026-44653 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only `VIEW` access to an MCP server can retrieve the server's decrypted admin-managed secrets through `GET /api/mcp/servers` and `GET /api/mcp/servers/:serverName`. EPSS estimates a 0.28% chance of exploitation in the next 30 days.
Description
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only `VIEW` access to an MCP server can retrieve the server's decrypted admin-managed secrets through `GET /api/mcp/servers` and `GET /api/mcp/servers/:serverName`. The returned config includes plaintext values for `apiKey.key` and `oauth.client_secret`. This allows viewers of a shared MCP server to exfiltrate the underlying provider credentials. Version 0.8..4 contains a patch. Other remediations include: never returning decrypted admin-managed secrets to non-owners; redacting apiKey.key and oauth.client_secret from all API responses consider returning only boolean presence indicators for secrets, similar to the auth-values route pattern; and, if owners need to edit configs without re-entering secrets, preserving secrets server-side and returning placeholders instead of plaintext.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Librechat | Librechat | < 0.8.4 |
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-6vqg-rgpm-qvf9Exploit, Mitigation, Vendor Advisory
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-6vqg-rgpm-qvf9Exploit, Mitigation, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-44653?
How severe is CVE-2026-44653?
How do I fix CVE-2026-44653?
How Strix Helps
- How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2026
- CVE-2026-44648SillyTavern is a locally installed user interface that allow…7.5
- CVE-2026-44649SillyTavern is a locally installed user interface that allow…9.8
- CVE-2026-4465A flaw has been found in D-Link DIR-513 1.10. The impacted e…8.8
- CVE-2026-44650SillyTavern is a locally installed user interface that allow…9.1
- CVE-2026-44651SillyTavern is a locally installed user interface that allow…6.9
- CVE-2026-44652SillyTavern is a locally installed user interface that allow…6.9
- CVE-2026-44654LibreChat is an enhanced ChatGPT clone that supports multipl…8.1
- CVE-2026-44655Mantis Bug Tracker (MantisBT) is an open source issue tracke…8.6
- CVE-2026-44656Vim is an open source, command line text editor. Prior to ve…5.3
- CVE-2026-44657Mantis Bug Tracker (MantisBT) is an open source issue tracke…7.5
- CVE-2026-44658Zen is a firefox-based browser. Prior to 1.19.12b, RSS feed …2.4
- CVE-2026-44659Zen is a firefox-based browser. Prior to 1.19.12b, the ZEN B…4.7
Are you affected by CVE-2026-44653?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
