CVE-2026-54033
Librechat server-side request forgery (SSRF)
- Published25 Jun 2026
Description
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.
CVSS 3.1 breakdown
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:NAffected products
Remediation
No fixed version is recorded in the NVD data. Check the vendor advisory for the latest guidance.
Related CVEs
Recent high-severity vulnerabilities sharing a weakness type.
Frequently asked
Is CVE-2026-54033 being actively exploited?
CVE-2026-54033 is not in the CISA KEV catalog. A public exploit reference exists, so treat it as exploitable. Its EPSS exploit probability is 0.35%.
How severe is CVE-2026-54033?
CVE-2026-54033 has a CVSS 3.1 base score of 7.7, rated high. EPSS estimates a 0.35% probability of exploitation.
Which products are affected by CVE-2026-54033?
Affected products include Librechat.
How do I fix CVE-2026-54033?
Apply the vendor's patch or advisory guidance, then verify no affected versions remain across your devices.
How Secuno handles this
Secuno correlates vulnerabilities like CVE-2026-54033 against the real software inventory on every managed device, as each hourly inventory arrives. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.
Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.