CVE-2026-31951 | LibreChat's MCP Server Header Injection Enables OAuth Token Theft

Exp

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.

Published: 2026-03-27 Last update: 2026-06-17 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-31951 is rated Exploit Available (50/100): CVSS Medium severity, with low exploitation likelihood (EPSS 0.24%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2026-31951

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2026-31951

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-15 0.03% 0.24% +0.21%
2 2026-03-28 — 0.03% —

Full EPSS history (2 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-31951

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
6.8 3.1 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:R)
A real person has to do something—click, install, enable—otherwise it doesn’t land.
Scope (S:C)
Breaking this can reach past the original component and bite other resources—bigger blast radius.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:N)
Service keeps running; no real outage angle.
 2.3 4.0 [email protected]
5.7 3.1 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:R)
A real person has to do something—click, install, enable—otherwise it doesn’t land.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:N)
Service keeps running; no real outage angle.
 2.1 3.6 [email protected]

Weakness enumeration for CVE-2026-31951

Affected software / configurations for CVE-2026-31951

Vendor Product Version Raw CPE
librechat librechat >= 0.8.2, < 0.8.3 cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:*
librechat librechat 0.8.3 cpe:2.3:a:librechat:librechat:0.8.3:rc1:*:*:*:*:*:*

References for CVE-2026-31951

cvelogic Threat Intelligence