Back to overview

CVE-2026-54033

HIGH Exploitation: PoC
7.7
CVSS 3.1
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.

Metadata

CVE ID
CVE-2026-54033
State
PUBLISHED
Assigner
GitHub_M
Reserved
2026-06-11 16:57 UTC
Published
2026-06-25 15:50 UTC
Last updated
2026-06-25 17:43 UTC
Primary CWE
CWE-918
CWE-918: Server-Side Request Forgery (SSRF)
Vendor / Product
danny-avila / LibreChat
Sources
cve.org  ·  NVD

Severity & Metrics

7.7 HIGH CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
SSVC — CISA Coordinator
Exploitation
PoC
Automatable
no
Tech. Impact
partial
Affected products (1)
VendorProductPlatformVersions
danny-avila LibreChat — < 0.8.4-rc1
Weakness (CWE)
CWESourceDescription
CWE-918 cna CWE-918: Server-Side Request Forgery (SSRF)
CVSS scores (1)
ScoreSeverityVersionSourceVector
7.7 HIGH 3.1 cna CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
References (1)
Back to overview