๐Ÿ›ก๏ธ CVE-2026-31951
๐ŸŸก CVSS 6.8 โ€” Medium โš ๏ธ Exploit Public CWE-200 NVD
6.8
CVSS Score
0 Low4 Medium7 High9 Critical10

Description

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.

Details

Severity MEDIUM
CVSS Score 6.8
CVSS Vector CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
CWE CWE-200
Public Exploit โš ๏ธ Yes
Source NVD
Published 2026-03-27
Updated 2026-06-02
Modified 2026-03-30
Fix URL N/A

Affected Packages

Software From version Fixed in
librechat โ€” โ€”

Similar Threats

Patch Gap Protection

Running software with known vulnerabilities?

BotEraser can help reduce exposure by blocking IPs associated with exploit activity โ€” even before a patch is available.

Start Free โ†’

No credit card required  ยท  Results in minutes

ⓘ Data Notice: The information presented above has been compiled from publicly available internet sources. Boteraser aggregates this data solely for informational purposes and does not independently classify, evaluate, or endorse any findings about the vulnerabilities listed. The accuracy and completeness of this information is the sole responsibility of the original publishers. Boteraser and its operators accept no liability for any decisions made based on this data.