CVE-2026-105697Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration
Updated under an hour ago ()
Does this affect you?
It affects langflow-ai langflow and 2 other products. Add what you run to find out whether that includes you.
EPSS puts the chance of exploitation in the next 30 days at 0.47%, higher than 39% of scored CVEs.
Do this next
Free account, 1 product
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.
- CVSS
- 9.9 CRITICAL (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
- Weakness (CWE)
- CWE-78
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- 0.47% (percentile 39)
- Assigned by
- GitHub_M
- NVD analysis
- Undergoing Analysis
- Record last updated
- Oct 9, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
langflow-ai langflow langflow_ai:langflow (from the name) | from 1.1.2, < 1.10.3 | CNA record |
langflow-ai langflow-base langflow_ai:langflow_base (from the name) | from 0.1.2, < 0.10.3 | CNA record |
langflow-ai lfx langflow_ai:lfx (from the name) | before 1.10.3 | CNA record |
References
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45x-refsource-confirm
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2x-refsource-misc
- https://github.com/langflow-ai/langflow/pull/12290x-refsource-misc
- https://github.com/langflow-ai/langflow/pull/14036x-refsource-misc
- https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1dx-refsource-misc
- https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0x-refsource-misc
- https://github.com/langflow-ai/langflow/releases/tag/v1.10.3x-refsource-misc
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystemx-refsource-misc
- https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcpx-refsource-misc
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.