UTC
Critical

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

CVE-2026-105697 · GHSA-w794-rj3p-xv45 · published 2026-10-07 · updated 2026-10-09

Severity
Critical
CVSS score
9.9
Chance of exploitation (EPSS)
1.5%
Fixed in
1.10.3
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

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.

What to do

Upgrade langflow to 1.10.3 or later, and langflow-base to 0.10.3 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

#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 (LDPRELOAD, NODEOPTIONS, PYTHONPATH, BASHENV, ...), and Docker isolation checks. #14036** (1.10.3) — moves the policy into 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: Later hardening (1.11.0, #13530) adds optional stricter modes for multi-tenant deployments.

Affected
PackageRegistryAffectedFixed in
langflowPyPI>= 1.1.2, < 1.10.31.10.3
langflow-basePyPI>= 0.1.2, < 0.10.30.10.3

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].