CVE-2026-54030

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a malicious MCP server to steal access tokens intended for a legitimate server. This vulnerability is fixed in 0.8.5.

CVSS v3 8.0 HIGH

8.0^/10

CVSS v3 : HIGH

Vector :

Exploitability : 1.6 / Impact : 5.8

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact NONE

Scope CHANGED

References

Link	Resource
https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23	Exploit Vendor Advisory
https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

OR	cpe:2.3:a:librechat:librechat::::::::
	cpe:2.3:a:librechat:librechat:0.8.5:rc1::::::

History

29 Jun 2026, 23:55

Type	Values Removed	Values Added
First Time		Librechat librechat Librechat
CPE		cpe:2.3:a:librechat:librechat:::::::: cpe:2.3:a:librechat:librechat:0.8.5:rc1::::::
References	~~() https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23 -~~	() https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23 - Exploit, Vendor Advisory

26 Jun 2026, 02:16

Type	Values Removed	Values Added
References	~~() https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23 -~~	() https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23 -

25 Jun 2026, 17:16

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-06-25 17:16

Updated : 2026-06-29 23:55

NVD link : CVE-2026-54030

Mitre link : CVE-2026-54030

CVE.ORG link : CVE-2026-54030

JSON object : View

Products Affected

librechat

librechat

CWE

CWE-346

Origin Validation Error

{"id": "CVE-2026-54030", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-54030", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-06-26T02:04:27.570333Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 8.0, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:N", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "HIGH", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.8, "exploitabilityScore": 1.6}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 9.3, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:N", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.8, "exploitabilityScore": 2.8}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "danny-avila", "product": "LibreChat", "versions": [{"status": "affected", "version": "< 0.8.5"}]}]}], "published": "2026-06-25T17:16:40.660", "references": [{"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23", "tags": ["Exploit", "Vendor Advisory"], "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-346"}]}], "descriptions": [{"lang": "en", "value": "LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a malicious MCP server to steal access tokens intended for a legitimate server. This vulnerability is fixed in 0.8.5."}], "lastModified": "2026-06-29T23:55:08.373", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "0DE16CB2-3414-4174-8CFA-D00EDF4FD096", "versionEndIncluding": "0.8.4"}, {"criteria": "cpe:2.3:a:librechat:librechat:0.8.5:rc1:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "10B1819A-4469-4605-9381-79BD1F6E6ADC"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}