CVE-2026-54033

What it is

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.

At a glance

Exploitability

Can be exploited over the network with a low-privilege account. High risk of data exposure.

Exploit odds

0.4% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-06-25 17:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-25 22:10 UTC Last updatedMost recent change to the record

Why it ranks here

• Exploited in the wild: no, CISA does not list it.
• Exploit odds: 0.4% in the next 30 days (EPSS).
• Severity: 7.7 HIGH (CVSS).
• Fix: a patch or advisory is linked.

Details

Published

2026-06-25 17:16 UTC

Last modified

2026-10-25 22:10 UTC

Exploit probability

0.4% · EPSS, next 30 days

Weakness

CWE-918 · Server-side request forgery

Record status

Analyzed

Affected

• Librechat ≤ 0.8.3

Attack profile CVSS 3.1 · 7.7

Attack vector

Network

Complexity

Low

Privileges needed

Low

User interaction

None

Scope

Changed

Confidentiality

High

Integrity

None

Availability

None

Is it in your code?

Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.

Read https://cve-list.com/agent/cve/CVE-2026-54033.md and follow it. Check whether this project is affected by CVE-2026-54033. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.

Copy as ticket · More options · Status badge