llamaCVEVulnerability Intelligence
/
Advisory · GitHub · PyPI · langflow

GHSA-W794-RJ3P-XV45

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

Parche disponible
Descargar PNG JSON
CVSS
—
critical
Fuente: —
ExplotaciónSin evidenciaNo figura en CISA KEV
Exploits públicos0Ninguno conocido
Parche2 versionesPrimer parche a -76 d de la divulgación
Exposición42 dDesde la divulgación, 7 oct 2026, 3:36 p. m.
Detección40 dDesde la divulgación hasta su ingreso al índice
Timeline

Ciclo de vida de la vulnerabilidad

Hoy
Divulgación
Publicada
Modificada
Explotación
Remediación
Parche 1.10.3 +1
Monitoreo
Detectada
23 jul 26
7 oct 26
15 oct 26
17 nov 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 · -76 d desde divulgación
Remediación Parche 0.10.3 langflow-base · -76 d desde divulgación
Divulgación Publicada GHSA-W794-RJ3P-XV45 divulgada
Divulgación Modificada Última actualización del registro
Monitoreo Detectada Ingresó al índice
Resumen
Descripción del advisory
Texto original · GitHub · en inglés
Summary

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.

The issue was fixed in two steps and is fully fixed in Langflow 1.10.3 (and 1.11.0+):

  • 1.9.0 — #12290 added a command allowlist and argument/env validation to the REST model (`MCPServerConfig`), blocking the "Add MCP Server" vector reported here.
  • 1.10.3 — #14036 applied the same policy at the execution sink (`lfx.base.mcp.util`), including configs embedded in flows / tweaks and the final pre-spawn boundary, and removed the `bash -c` wrapper (the process is now exec'd directly, without a shell).
Affected versions

| Package (PyPI) | Vulnerable | Patched |
|---|---|---|
| `langflow` | `>= 1.1.2, < 1.10.3` | `1.10.3` |
| `langflow-base` | `>= 0.1.2, < 0.10.3` | `0.10.3` |
| `lfx` | `< 1.10.3` | `1.10.3` |

| Release | State |
|---|---|
| `1.1.2` – `1.4.x` | MCP Stdio component (added in #5148) runs `StdioServerParameters(command=..., args=...)` from the component's `command` field with no validation. |
| `1.5.0` – `1.8.x` | "Add MCP Server" settings page and `/api/v2/mcp/servers` API added (#8388). Stored stdio configs are launched via `bash -c "exec {command_str} ..."` with no validation. The PoC below works as-is. |
| `1.9.0` – `1.10.2` | #12290: `POST`/`PATCH /api/v2/mcp/servers` reject commands outside the allowlist. The execution sink still has no validation and still uses `bash -c`, so configs that do not go through `MCPServerConfig` (for example an MCP Tools component value embedded in a flow or passed as a tweak) can still execute arbitrary commands. |
| `1.10.3`+ | #14036: one shared policy (`lfx.base.mcp.security.validate_mcp_stdio_config`) is enforced at the API, at flow execution and right before the process is spawned; no shell is used. Fixed. |

Details

Vulnerable sink (`src/lfx/src/lfx/base/mcp/util.py`, `MCPStdioClient._connect_to_server`, before 1.10.3):

server_params = StdioServerParameters(
    command="bash",
    args=["-c", f"exec {command_str} || echo 'Command failed with exit code $?' >&2"],
    env=env_data,
)

`command_str` is built from the user's `command` + `args`. The only "validation" before 1.9.0 was `_validate_node_installation`, which only checks that Node.js is installed when the command contains `npx`. The MCP SDK then starts the process with `anyio.open_process`, so the command runs before any MCP handshake — which is why it executes even if the UI shows "failed to start".

PoC (as reported, Langflow 1.5.0 – 1.8.x)

In "Add MCP Server" → STDIO, add:

Name      - Test
Command   - touch
Arguments - /tmp/pwn

Or through the API, using a token from `auto_login` (default configuration):

TOKEN=$(curl -s http://127.0.0.1:7860/api/v1/auto_login | python3 -c 'import sys,json;print(json.load(sys.stdin)["access_token"])')

curl -s -X POST 'http://127.0.0.1:7860/api/v2/mcp/servers/testing' \
  -H "Authorization: Bearer $TOKEN" \
  -H 'Content-Type: application/json' \
  --data-raw '{"command":"touch","args":["/tmp/pwned_langflow"]}'

`/tmp/pwned_langflow` gets created on the server. On 1.10.3+ the request is rejected with `Command 'touch' is not allowed for security reasons. Allowed commands: bash, cmd, docker, node, npx, python, python3, uvx`, and the same payload fails at the sink (`MCPStdioClient.connect_to_server("touch /tmp/pwned_langflow")` raises `MCPStdioSecurityError`, and no file is created). Wrappers such as `bash -c "touch ..."`, `sh -c ...`, `python3 -c ...` and `node -e ...` are also rejected.

Fix
  • #12290 (1.9.0) — `MCPServerConfig` validators: command allowlist (`node`, `python`, `python3`, `npx`, `uvx`, `docker`, and `cmd`/`sh`/`bash` only to wrap one of those), shell-metacharacter and dangerous-keyword checks on arguments, env var blocklist (`LD_PRELOAD`, `NODE_OPTIONS`, `PYTHONPATH`, `BASH_ENV`, ...), and Docker isolation checks.
  • #14036 (1.10.3) — moves the policy into `lfx.base.mcp.security.validate_mcp_stdio_config` and enforces it at every entry point (API, embedded flow / tweak configs, the deprecated MCP Stdio component and just before spawn); it also launches the process without a shell:
command_parts = shlex.split(command_str)
command, args = command_parts[0], command_parts[1:]
validate_mcp_stdio_config(command, args, env)   # final pre-spawn enforcement
server_params = StdioServerParameters(command=command, args=final_args, env=env_data)

Later hardening (1.11.0, #13530) adds optional stricter modes for multi-tenant deployments.

Workarounds (if you cannot upgrade)
  • Set `LANGFLOW_AUTO_LOGIN=false` and do not expose Langflow directly to untrusted networks.
  • Only give Langflow accounts to trusted users.
Hardening recommendations for 1.10.3+

The allowlist still lets `npx` / `uvx` run any package by default, which is how MCP servers are normally distributed. On multi-tenant deployments, operators should also set:

  • `LANGFLOW_MCP_SERVER_ALLOWED_PACKAGES` — the exact packages `npx` / `uvx` may run.
  • `LANGFLOW_MCP_SERVER_INTERPRETER_HARDENING=true` and `LANGFLOW_MCP_SERVER_DOCKER_HARDENING=true`.
  • On 1.11.1+ (#14150), restricting custom code (`LANGFLOW_ALLOW_CUSTOM_COMPONENTS=false`, `LANGFLOW_CUSTOM_COMPONENT_ADMIN_ONLY=true` or `LANGFLOW_BLOCK_CODE_INTERPRETER_COMPONENTS=true`) also limits MCP stdio servers to superusers.
Impact

Remote code execution on the Langflow host as the Langflow process user (CWE-78). Any exposed instance on a vulnerable version is affected, whether the attacker has an account or uses the default `AUTO_LOGIN`. The reporter found several internet-facing Langflow servers that were vulnerable.

Incluye detalles técnicos publicados por el investigador. Úselos solo para validar y corregir sus propios sistemas.

Versiones

Rangos afectados

Afectada Corregida Última
lfx< 1.10.3
langflow-base≥ 0.1.2 < 0.10.3
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 -76 d 1.13.2 no afectada
pypilangflow-base
Corregida 0.10.3 -76 d 1.13.2 no afectada
pypilfx
Corregida 1.10.3 -76 d 1.13.2 no afectada
Versiones corregidas0.10.31.10.3
Explotación

Arsenal público

Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.

Referencias
Advisoryhttps://nvd.nist.gov/vuln/detail/CVE-2026-105697
Otrahttps://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2
Otrahttps://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45
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
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.