CVE-2026-54031
LibreChat server-side request forgery in MCP OAuth redirect handling
An attacker with low-privilege access can reach internal services that should be blocked, with no user action.
Texto original en inglés · Ver en español
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
Fuente: CNA
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Divulgación | Publicada | CVE-2026-54031 divulgada · CVSS 6.3 (CNA) | |
| Monitoreo | Detectada | Ingresó al índice | |
| Monitoreo | Fuente: NIST NVD | Registro visto por primera vez en NIST NVD | |
| Monitoreo | Verificada | Última verificación contra las fuentes |
LibreChat, the AI chat application, has a flaw in how it handles MCP OAuth requests: after checking the first destination for internal addresses, it follows redirects without checking where they lead. An attacker who has low-privilege access and can start an MCP OAuth flow against a server they control can reach remotely, without user action, internal or private services that those checks should block.
Descripción original del registro (GitHub_M)
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.8, packages/api/src/mcp/oauth/handler.ts createOAuthFetch validates only the initial destination for MCP OAuth discovery, registration, token, refresh, and revocation requests, then uses redirect-following fetch behavior without validating each redirect target. An attacker who can initiate MCP OAuth against a controlled endpoint can redirect server requests to internal or private addresses, reaching services that the initial SSRF checks should block. The separate MCP transport path already validates redirects and is not affected. This issue is fixed in version 0.8.8.
Desglose de métricas
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
LibreChat |
Corregida | 0.8.8 | — | — |
0.8.8Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-f7xq-83jc-cgrjhttps://www.librechat.ai/changelog/v0.8.8https://github.com/LibreChat-AI/LibreChat/pull/16514https://github.com/LibreChat-AI/LibreChat/commit/4d33d8c2c71ad497fdfaa2c4334b0a2293bcbd67https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
