TI-2025-40883 Aliases CVE-2025-66451

LibreChat's Improper Input Validation in Prompt Creation API Enables Unauthorized Permission Changes

MEDIUM 57CWE-20Published 2025-12-11 · Updated 2025-12-12

Key facts

Attack vector: Network
Privileges required: None
User interaction: Passive
Attack complexity: Low
Attack requirements: None
Impact type: Tampering
Confidentiality · integrity · availability: Low · Low · None
Fix status: Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-915.

Summary

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV

EPSS 0.00333 26th percentileScored 2026-11-07

Public exploit Yes 1 exploit referenceTagged by NVD

Fix Fixed LibreChat (danny-avila): 0.8.1

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation: Poc
Automatable: No
Technical impact: Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

Vendor	Product	Affected versions	Fixed in	Status	Source
danny-avila	LibreChat	before 0.8.1	0.8.1	Patch available	CNA

LibreChat Vendordanny-avila Affected before 0.8.1 Fixed in 0.8.1 Patch available CNA

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:librechat:librechat::::::::	before 0.8.1	Vulnerable	danny-avila

cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:* Versions before 0.8.1 Vulnerable ·danny-avila

Remediation

Fix · CNA LibreChat (danny-avila) Fixed in 0.8.1

Timeline

2026-10-02 Threatist record created from CVE-2025-66451

References

Exploit 1

https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vpqq-5qr4-655h

Patch 1

https://github.com/danny-avila/LibreChat/commit/01413eea3d3c1454d32ca9704fa9640407839737

TI-2026-25134 LibreChat Exfiltrates Server Secrets via MCP Server URL Injection CVSS 3.1CRITICAL 9.6
TI-2026-17862 LibreChat MCP Stdio Remote Command Execution CVSS 3.1CRITICAL 9.9
TI-2026-38976 LibreChat: Missing Resource Parameter Validation in MCP OAuth Flow CVSS 3.1CRITICAL 9.3
TI-2024-27763 LibreChat through 0.7.4-rc1 has incorrect access control for message updates. CVSS 3.1CRITICAL 9.8
TI-2024-10347 Path Traversal in danny-avila/librechat CVSS 3.0HIGH 8.8
TI-2026-25682 In LibreChat 0.8.1-rc2, a logged-in user obtains a JWT for both the LibreChat API and the RAG API. CVSS 3.1CRITICAL 9.0

See all 50 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences