CVE-2026-31944

{"id": "CVE-2026-31944", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-31944", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-03-16T13:40:08.924691Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 7.6, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N", "integrityImpact": "LOW", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 4.7, "exploitabilityScore": 2.3}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "danny-avila", "product": "LibreChat", "versions": [{"status": "affected", "version": ">= v0.8.2, <= 0.8.2-rc3"}]}]}], "published": "2026-03-13T19:54:39.590", "references": [{"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-306"}]}], "descriptions": [{"lang": "en", "value": "LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim\u2019s OAuth tokens are stored on the attacker\u2019s LibreChat account, enabling account takeover of the victim\u2019s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1."}, {"lang": "es", "value": "LibreChat es un clon de ChatGPT con caracter\u00edsticas adicionales. Desde 0.8.2 hasta 0.8.2-rc3, el endpoint de callback OAuth de MCP (Model Context Protocol) acepta la redirecci\u00f3n del proveedor de identidad y almacena tokens OAuth para el usuario que inici\u00f3 el flujo, sin verificar que el navegador que accede a la URL de redirecci\u00f3n est\u00e9 logueado o que el usuario logueado coincida con el iniciador. Un atacante puede enviar la URL de autorizaci\u00f3n a una v\u00edctima; cuando la v\u00edctima completa el flujo, los tokens OAuth de la v\u00edctima se almacenan en la cuenta de LibreChat del atacante, permitiendo la toma de control de la cuenta de los servicios vinculados a MCP de la v\u00edctima (p. ej., Atlassian, Outlook). Esta vulnerabilidad se corrige en 0.8.3-rc1."}], "lastModified": "2026-06-17T10:34:49.150", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:librechat:librechat:0.8.2:-:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "8D828ED6-3F44-4DD1-B29F-62D8977AF33A"}, {"criteria": "cpe:2.3:a:librechat:librechat:0.8.2:rc1:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "8E26DE8F-E11A-4052-B9FE-59AD6B9AFD03"}, {"criteria": "cpe:2.3:a:librechat:librechat:0.8.2:rc2:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "21865C8B-C628-4275-A552-89F64EF22918"}, {"criteria": "cpe:2.3:a:librechat:librechat:0.8.2:rc3:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "47A1B487-1A7B-4E06-8503-56E7D349FAA2"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}