langflow-ai Langflow/langflow-base/lfx MCP Stdio Transport /api/v2/mcp/servers server_name/command os command injection

Summaryinfo

A vulnerability identified as critical has been detected in langflow-ai Langflow, langflow-base and lfx. Affected by this issue is some unknown functionality of the file /api/v2/mcp/servers of the component MCP Stdio Transport. This manipulation of the argument server_name/command causes os command injection. This vulnerability is handled as CVE-2026-105697. The attack can be initiated remotely. There is not any exploit available.

Detailsinfo

A vulnerability classified as critical was found in langflow-ai Langflow, langflow-base and lfx (affected version not known). Affected by this vulnerability is some unknown functionality of the file /api/v2/mcp/servers of the component MCP Stdio Transport. The manipulation of the argument server_name/command with an unknown input leads to a os command injection vulnerability. The CWE definition for the vulnerability is CWE-78. The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

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.

The advisory is shared at github.com. This vulnerability is known as CVE-2026-105697 since 10/05/2026. The exploitation appears to be easy. The attack can be launched remotely. Technical details are known, but no exploit is available. The price for an exploit might be around USD $0-$5k at the moment (estimation calculated on 10/05/2026). MITRE ATT&CK project uses the attack technique T1202 for this issue.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• langflow-ai

Name

• Langflow
• langflow-base
• lfx

Website

• Product: https://github.com/langflow-ai/langflow/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion