Langflow: OS command injection via MCP stdio server configuration
Summary
Langflow, a platform for building AI agents and workflows, runs the command and arguments of an MCP stdio server configuration on the host without an allowlist before version 1.10.3. A user who can change MCP server settings or build flows with the MCP Tools component can run arbitrary OS commands on the Langflow host as the Langflow process user once Langflow connects to that server. With the default LANGFLOW_AUTO_LOGIN=true, an exposed instance can be attacked without an account; with auto-login disabled, any authenticated non-admin user can exploit it.
Affected
- langflow (langflow-ai): >= 1.1.2, < 1.10.3
- langflow-base: >= 0.1.2, < 0.10.3
- lfx: < 1.10.3
Fixed in
- langflow 1.10.3
- langflow-base 0.10.3
- lfx 1.10.3
Workaround
- Disable LANGFLOW_AUTO_LOGIN (a development-only setting) so that no token is issued without credentials.
- Restrict who can add or change MCP server configurations and MCP Tools components.
- These are compensating controls, not a fix.
Exploitation
- CISA SSVC: Exploitation none, Automatable no.
- No confirmed in-the-wild exploitation or public proof of concept for CVE-2026-105697 was found in the sources reviewed.
- Reports of exploitation concern the related CVE-2026-105740, which shares the code path. These are secondary reports and unverified.
Our recommendation
- Upgrade to Langflow 1.10.3, langflow-base 0.10.3 or lfx 1.10.3 (or later).
- Until patched, set LANGFLOW_AUTO_LOGIN=false and do not expose Langflow directly to the internet.
- Review stored MCP server entries for unexpected commands and check logs for requests to /api/v2/mcp/servers/.
- Monitor the Langflow host for shells or network tools started by the Langflow process and restrict its outbound connections.
Public exploits
Links to third-party sites, not checked by us – exploit code can contain malware. Only use it in isolated test environments.
- Proof of concept on GitHub (1 repositories)
Iceman2050/mcp-patch-gap-scanner
Research sources
- GitHub commit eba285e: harden MCP stdio configuration github.com
- GitHub commit efbc4a1: prevent MCP command injection via allowlist validation github.com
- GitHub pull request #14036 github.com
- Langflow release v1.10.3 github.com
- GitHub Security Advisory GHSA-w794-rj3p-xv45 github.com
- Strix CVE record CVE-2026-105697 www.strix.ai
- TheHackerWire: CVE-2026-105697 www.thehackerwire.com
Researched and written up in English and German by an AI (Claude by Anthropic) based on NVD, CISA, EPSS and the sources listed. The vendor information is authoritative. Researched on 30 Oct 2026, 15:41.
Original description (NVD)
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.
NVD references (9)
- https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d
- https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0
- https://github.com/langflow-ai/langflow/pull/12290
- https://github.com/langflow-ai/langflow/pull/14036
- https://github.com/langflow-ai/langflow/releases/tag/v1.10.3
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem
- https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-o…
Sources
The tracker combines official, freely usable data sources – updated continuously:
- NVD (NIST) – CVEs, rating (CVSS), affected products
- CISA KEV – vulnerabilities confirmed by CISA as actively exploited
- CISA Vulnrichment – CISA assessment (SSVC) in the official CVE record
- FIRST EPSS – probability of exploitation
- Microsoft MSRC – Patch Tuesday: vulnerabilities, severity, updates
- PoC-in-GitHub – public proof-of-concept repositories
- Metasploit (Rapid7) – modules of the Metasploit Framework
- Exploit-DB (OffSec) – archive of public exploits (links only)
- Patch days: official vendor pages (linked per vendor) (Vendor patch days)
This product uses data from the NVD API but is not endorsed or certified by the NVD. EPSS data © FIRST.org.
Affected? We can help.
We check whether your systems are affected, install updates and close the gap – continuously with the System Health Checker if you wish.