CVE-2026-54033: LibreChat: SSRF via User-Provided Custom Endpoint baseURL — no private IP validation on user-configured API base URLs
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, LibreChat allows users to configure custom OpenAI-compatible API endpoints by setting a baseURL. This URL is used to construct HTTP requests without any SSRF validation — no private IP check, no scheme restriction, no DNS pinning. An authenticated user can set baseURL to internal network addresses. This vulnerability is fixed in 0.8.4-rc1.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
LibreChatto a version that resolves this vulnerability.Fixed in 0.8.4-rc1
Event History
Frequently Asked Questions
What is the severity of CVE-2026-54033?
The severity of CVE-2026-54033 is classified as high with a score of 7.7.
What type of vulnerability is CVE-2026-54033?
CVE-2026-54033 is classified as a Server-Side Request Forgery (SSRF) vulnerability.
How do I fix CVE-2026-54033?
To fix CVE-2026-54033, update LibreChat to version 0.8.4-rc1 or later where the SSRF vulnerability is addressed.
What impact does CVE-2026-54033 have?
CVE-2026-54033 can lead to unauthorized access to internal services through user-configured API base URLs.
Which software is affected by CVE-2026-54033?
CVE-2026-54033 affects LibreChat versions prior to 0.8.4-rc1.