CVE-2026-31951

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.

CVSS v3 6.8 MEDIUM

6.8^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 2.3 / Impact : 4.0

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact NONE

Availability Impact NONE

Scope CHANGED

References

Link	Resource
https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

OR	cpe:2.3:a:librechat:librechat::::::::
	cpe:2.3:a:librechat:librechat:0.8.3:rc1::::::

History

26 Oct 2026, 21:10

Type	Values Removed	Values Added
Summary		(es) LibreChat es un clon de ChatGPT con características adicionales. En las versiones 0.8.2-rc1 a 0.8.3-rc1, los servidores MCP (Model Context Protocol) creados por el usuario pueden incluir encabezados HTTP arbitrarios que sufren sustitución de marcadores de posición de credenciales. Un atacante puede crear un servidor MCP malicioso con encabezados que contienen ’{{LIBRECHAT_OPENID_ACCESS_TOKEN}}’ (y otros), lo que provoca que las víctimas que llaman a herramientas en ese servidor vean sus tokens OAuth exfiltrados. La versión 0.8.3-rc2 corrige el problema.

Information

Published : 2026-03-27 20:16

Updated : 2026-10-26 21:10

NVD link : CVE-2026-31951

Mitre link : CVE-2026-31951

CVE.ORG link : CVE-2026-31951

JSON object : View

Products Affected

librechat

librechat

CWE

CWE-200

Exposure of Sensitive Information to an Unauthorized Actor

{"id": "CVE-2026-31951", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-31951", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-03-31T13:45:16.896153Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 6.8, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 4.0, "exploitabilityScore": 2.3}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 5.7, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 3.6, "exploitabilityScore": 2.1}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "danny-avila", "product": "LibreChat", "versions": [{"status": "affected", "version": ">= v0.8.2-rc1, <= v0.8.3-rc1"}]}]}], "published": "2026-03-27T20:16:30.397", "references": [{"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-200"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "LibreChat es un clon de ChatGPT con caracter\u00edsticas adicionales. En las versiones 0.8.2-rc1 a 0.8.3-rc1, los servidores MCP (Model Context Protocol) creados por el usuario pueden incluir encabezados HTTP arbitrarios que sufren sustituci\u00f3n de marcadores de posici\u00f3n de credenciales. Un atacante puede crear un servidor MCP malicioso con encabezados que contienen \u2019{{LIBRECHAT_OPENID_ACCESS_TOKEN}}\u2019 (y otros), lo que provoca que las v\u00edctimas que llaman a herramientas en ese servidor vean sus tokens OAuth exfiltrados. La versi\u00f3n 0.8.3-rc2 corrige el problema."}], "lastModified": "2026-10-26T21:10:00.170", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "0B0F03AD-B51B-4501-B292-3133DBD964A8", "versionEndExcluding": "0.8.3", "versionStartIncluding": "0.8.2"}, {"criteria": "cpe:2.3:a:librechat:librechat:0.8.3:rc1:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "482D0FE3-2AB3-47B6-982E-564A5B824464"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}