llamaCVEVulnerability Intelligence
/
langflow

CVE-2026-105697

Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Specific setups onlyParche disponible
Descargar PNG JSON
CVSS 3.1
9.9
Crítica
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H Fuente: CNA
ExplotaciónSin evidenciaSSVC: none · no figura en CISA KEV
Exploits públicos11 fuente
Parche2 versionesPrimer parche a -74 d de la divulgación
Exposición44 dDesde la divulgación, 5 oct 2026, 3:16 p. m.
Detección17 dDesde la divulgación hasta su ingreso al índice
Decisión SSVCSeguir de cerca
Monitorear y programar la remediación
Sin explotación conocida, no automatizable e impacto técnico total. Hay versiones corregidas disponibles.
Timeline

Ciclo de vida de la vulnerabilidad

Hoy
Divulgación
Publicada
Evaluación SSVC
Modificada
Explotación
Remediación
Parche 1.10.3 +1
Monitoreo
Detectada
Fuente: PoC-in-GitHub
23 jul 26
5 oct 26
6 oct 26
9 oct 26
22 oct 26
30 oct 26
19 nov 26
23 jul 26
22 ago 26
21 sept 26
20 oct 26
19 nov 26
FechaFaseEventoDetalle
Remediación Parche 1.10.3 langflow · -74 d desde divulgación
Remediación Parche 0.10.3 langflow-base · -74 d desde divulgación
Divulgación Publicada CVE-2026-105697 divulgada · CVSS 9.9 (CNA)
Divulgación Evaluación SSVC CISA-ADP · explotación ninguna
Divulgación Modificada Última actualización del registro
Monitoreo Detectada Ingresó al índice
Monitoreo Fuente: PoC-in-GitHub Registro visto por primera vez en PoC-in-GitHub
Resumen

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to reach the MCP server settings ("Settings → MCP Servers → Add MCP Server", POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a "server" whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow) — even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3.

Langflow from 1.1.2 before 1.10.3 is affected, through the MCP stdio server settings and the MCP Tools component, with langflow-base and lfx also in scope. Fixed in Langflow 1.10.3.

¿Qué significa?The MCP stdio server configuration accepts an arbitrary command that Langflow runs on the host operating system. This lets a user execute arbitrary OS commands as the Langflow process user.
¿Quién está afectado?Langflow versions from 1.1.2 before 1.10.3 are affected, as are langflow-base from 0.1.2 before 0.10.3 and lfx before 1.10.3. Check the installed version with pip show langflow or your package manager. With the default LANGFLOW_AUTO_LOGIN=true no account is needed, while with it set to false an authenticated non-admin user is required.
¿Qué hacer?Upgrade to Langflow 1.10.3, which the advisory says fully fixes the issue. Until the upgrade, set LANGFLOW_AUTO_LOGIN=false and do not expose Langflow directly to untrusted networks.
Contexto

Condiciones y alcance

Condiciones necesarias para que el fallo sea explotable
01
Langflow version before 1.10.3 (from 1.1.2)“Before Langflow 1.10.3”
02
Attacker must be able to reach the MCP server settings or build a flow with the MCP Tools component“Any user able to reach the MCP server settings”
03
With the default LANGFLOW_AUTO_LOGIN=true, no account is needed; with it disabled, an authenticated non-admin user is required“With the default LANGFLOW_AUTO_LOGIN=true”
MitigaciónSet LANGFLOW_AUTO_LOGIN=false and do not expose Langflow directly to untrusted networks
Vector CVSS 3.1

Desglose de métricas

Opción resaltada = valor del vector · izquierda = peor caso · CNA
Vector de ataqueAV:N
RedAdyacenteLocalFísica
ComplejidadAC:L
BajaAlta
PrivilegiosPR:L
NingunoBajosAltos
InteracciónUI:N
NingunaRequerida
AlcanceS:C
CambiadoSin cambio
ConfidencialidadC:H
AltoBajoNinguno
IntegridadI:H
AltoBajoNinguno
DisponibilidadA:H
AltoBajoNinguno
Versiones

Rangos afectados

Afectada Corregida Última
lfx< 1.10.3
langflow-base≥ 0.1.2 < 0.10.3
lfx · langflow≥ 1.1.2 < 1.10.3
0.1.2
0.10.3
1.1.2
1.10.3
1.13.2
Remediación

Estado del parche por paquete

Paquete / productoEstadoCorregida enDesde divulgaciónÚltima versión
pypilangflow
Corregida 1.10.3 -74 d 1.13.2 no afectada
pypilangflow-base
Corregida 0.10.3 -74 d 1.13.2 no afectada
pypilfx
Corregida 1.10.3 -74 d 1.13.2 no afectada
Versiones corregidas0.10.31.10.3
Explotación

Arsenal público

Exploit-DB
—
0
Metasploit
—
0
Nuclei
—
0
PoC en GitHub
Iceman2050/mcp-patch-gap-scanner
1
Ver los 1 repositorios de GitHub
Iceman2050/mcp-patch-gap-scanner

Los repositorios públicos incluyen exploits, escáneres, laboratorios y reglas de detección. No ejecute código de terceros sin revisarlo en un entorno aislado.

Referencias
Fabricantehttps://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45
Fabricantehttps://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2
Exploithttps://github.com/Iceman2050/mcp-patch-gap-scanner
Otrahttps://github.com/langflow-ai/langflow/pull/12290
Otrahttps://github.com/langflow-ai/langflow/pull/14036
Otrahttps://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d
Otrahttps://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0
Otrahttps://github.com/langflow-ai/langflow/releases/tag/v1.10.3
Otrahttps://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem
Otrahttps://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp

Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.