CVE-2026-105697: Command Injection (CVSS 9.9)

Description

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.

Is your site exposed to CVE-2026-105697?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

9.9

CRITICAL

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

EPSS — Exploit Prediction

0.0047

Probability of exploitation

0.39%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-78 OS Command Injection

References

Other References

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-of-the-mcp

Frequently Asked Questions

What is CVE-2026-105697? +

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. It has a CVSS v3.1 base score of 9.9 (CRITICAL).

How severe is CVE-2026-105697? +

CVE-2026-105697 has a CVSS v3.1 score of 9.9 out of 10, rated CRITICAL. This is a critical vulnerability that should be patched immediately. The EPSS score is 0.0047, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-105697? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2024-54012

Penetration Testing engineers at Amazon discovered a vulnerability where the camera system failed to properly validate input, allowing specially crafted …

CVE-2026-8652

An OS Command Injection vulnerability exists in Aterm. If a malicious third person gains administrator access to the product’s web …

CVE-2026-34007

An OS command injection vulnerability has been reported to affect Notes Station 3. If exploited, the vulnerability could allow remote …

CVE-2025-13605

3onedata modbus gateway device model GW1101-1D(RS-485)-TB-P (hardware version V2.2.0) allows authenticated users to execute arbitrary shell commands in the context …

CVE-2026-41925

WDR201A WiFi Extender (HW V2.1, FW LFMZX28040922V1.02) contains an OS command injection vulnerability in the adm.cgi binary's reboot_time function that …

CVE-2026-41924

WDR201A WiFi Extender (HW V2.1, FW LFMZX28040922V1.02) contains an OS command injection vulnerability in the makeRequest.cgi binary that allows unauthenticated …

CVE-2026-105697