CVE-2025-66451 LibreChat's Improper Input Validation in Prompt Creation API Enables Unauthorized Permission Changes

Medium 5.3 Published 11 Dec 2025 Updated 12 Dec 2025

Attackers can modify prompt groups via unvalidated API requests, leading to unauthorized data changes and potential privilege escalation in LibreChat.

Exploited in the wild: Not known
Login needed: Not needed
Attackable: Over the internet
Victim action needed: A user has to click or open something
Fix: None listed

What is CVE-2025-66451?

CVE-2025-66451 is a medium-severity missing authorization vulnerability in Librechat Librechat, published on 11 Dec 2025. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

Official description

LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when creating prompts, JSON requests are sent to define and modify the prompts via PATCH endpoint for prompt groups (/api/prompts/groups/:groupId). However, the request bodies are not sufficiently validated for proper input, enabling users to modify prompts in a way that was not intended as part of the front end system. The patchPromptGroup function passes req.body directly to updatePromptGroup() without filtering sensitive fields. This issue is fixed in version 0.8.1.

Weakness: CWE-915, CWE-20

Which versions are affected by CVE-2025-66451?

It affects 1 product.

Products include Librechat Librechat.

How do I fix CVE-2025-66451?

No fix has been published for CVE-2025-66451 yet. Limit exposure of the affected software until one is available.

Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.

Is CVE-2025-66451 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-66451 exists.

All Librechat Librechat vulnerabilities

Sources

Also known as GHSA-vpqq-5qr4-655h.