danny-avila LibreChat up to 0.8.3-rc1 Model Context Protocol information disclosure
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 5.1 | $0-$5k | 0.47 |
Summary
A vulnerability classified as problematic was found in danny-avila LibreChat up to 0.8.3-rc1. This affects an unknown function of the component Model Context Protocol. Such manipulation leads to information disclosure. This vulnerability is uniquely identified as CVE-2026-31951. The attack can be launched remotely. No exploit exists. Upgrading the affected component is advised.
Details
A vulnerability was found in danny-avila LibreChat up to 0.8.3-rc1. It has been rated as problematic. Affected by this issue is an unknown function of the component Model Context Protocol. The manipulation with an unknown input leads to a information disclosure vulnerability. Using CWE to declare the problem leads to CWE-200. The product exposes sensitive information to an actor that is not explicitly authorized to have access to that information. Impacted is confidentiality. CVE summarizes:
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.
The advisory is shared for download at github.com. This vulnerability is handled as CVE-2026-31951 since 03/10/2026. The exploitation is known to be easy. The attack may be launched remotely. Successful exploitation requires user interaction by the victim. There are neither technical details nor an exploit publicly available. The MITRE ATT&CK project declares the attack technique as T1592.
Upgrading to version 0.8.3-rc2 eliminates this vulnerability.
If you want to get best quality of vulnerability data, you may have to visit VulDB.
Product
Type
Vendor
Name
Version
Website
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 5.1VulDB Meta Temp Score: 5.1
VulDB Base Score: 3.5
VulDB Temp Score: 3.4
VulDB Vector: 🔒
VulDB Reliability: 🔍
CNA Base Score: 6.8
CNA Vector (GitHub_M): 🔒
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Information disclosureCWE: CWE-200 / CWE-284 / CWE-266
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
EPSS Score: 🔒
EPSS Percentile: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: UpgradeStatus: 🔍
0-Day Time: 🔒
Upgrade: LibreChat 0.8.3-rc2
Timeline
03/10/2026 CVE reserved03/27/2026 Advisory disclosed
03/27/2026 VulDB entry created
03/27/2026 VulDB entry last update
Sources
Product: github.comAdvisory: GHSA-pmw7-gqwj-f954
Status: Confirmed
CVE: CVE-2026-31951 (🔒)
GCVE (CVE): GCVE-0-2026-31951
GCVE (VulDB): GCVE-100-354032
Entry
Created: 03/27/2026 23:44Changes: 03/27/2026 23:44 (66)
Complete: 🔍
Cache ID: 216:DCC:103
No comments yet. Languages: en.
Please log in to comment.