Not classified

Langflow MCP-config RCE (GHSA-7w94-79vh-5mr2, GHSA-w794-rj3p-xv45)

GHSA-7w94-79vh-5mr2 (CVE-2026-105697) and GHSA-w794-rj3p-xv45: Authenticated Langflow users can achieve RCE by adding MCP server with Stdio transport. User-supplied command field passed directly to bash -c…

What happened

GHSA-7w94-79vh-5mr2 (CVE-2026-105697) and GHSA-w794-rj3p-xv45: Authenticated Langflow users can achieve RCE by adding MCP server with Stdio transport. User-supplied command field passed directly to bash -c 'exec {command}' with zero validation, no allowlisting, no sandboxing. Env field allows arbitrary environment variable injection (LD_PRELOAD, PATH override). Command executes when server list fetched with action_count=true - happens automatically in UI MCP settings page. Affects <1.9.0 (GHSA-7w94-79vh-5mr2) and <1.10.3 (GHSA-w794-rj3p-xv45). Default LANGFLOW_AUTO_LOGIN=true hands out token without credentials. Previdian honeypots recorded 1,423 exploitation attempts from 27 IPs (Belgium, China, Germany, Hong Kong, Japan, Nigeria, Philippines, Russia, Seychelles, Singapore, South Korea, Taiwan, Tanzania, US, Vietnam) beginning Sep 19, 2026. Attackers first checked auto-login, then brute-forced credentials. Fixed in 1.9.0 (command allowlist) and 1.10.3 (full policy enforcement, removed bash wrapper). GitHub: github.com/langflow-ai/langflow.

Authenticated RCE via MCP Stdio server configuration allows arbitrary OS command execution on Langflow AI workflow platform

Read the original sourceAdditional source: GHSA-w794-rj3p-xv45: OS command injection RCE via MCP stdioAdditional source: Langflow Critical Authenticated RCE Flaw TargetedAdditional source: VulnCheck - Pwning the AI Stack

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Obtain authentication

    Default LANGFLOW_AUTO_LOGIN=true provides token without credentials via GET /api/v1/auto_login; or brute-force credentials if auto-login disabled

    Source for step 1
  2. 02 · Add malicious MCP server

    POST/PATCH /api/v2/mcp/servers/{server_name} with Stdio transport; command field contains arbitrary OS command (reverse shell, file operations, etc.); env field can inject LD_PRELOAD, PATH override

    Source for step 2
  3. 03 · Trigger execution

    Command executes automatically when GET /api/v2/mcp/servers?action_count=true (happens when anyone navigates to MCP settings page); re-executes every time list loaded; persistent backdoor

    Source for step 3
  4. 04 · Remote code execution

    User-supplied command wrapped in bash -c 'exec {command}' and executed; no validation, allowlisting, or sandboxing; runs with Langflow process privileges; full server compromise possible

    Source for step 4

Why it matters

Reported entry point: Authenticated user access (or LANGFLOW_AUTO_LOGIN=true provides token without credentials); exploitation via POST/PATCH /api/v2/mcp/servers/{server_name} or embedded flow configs. Reported impact: User-supplied command wrapped in bash -c 'exec {command}' and executed; no validation, allowlisting, or sandboxing; runs with Langflow process privileges; full server compromise possible; reported targets include Langflow installations; multiple internet-facing vulnerable instances found; 1,423 exploitation attempts against Previdian honeypots from 27 countries; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Upgrade to Langflow 1.10.3+; disable LANGFLOW_AUTO_LOGIN; enforce strong unique passwords; review MCP server configurations; monitor /api/v2/mcp/servers/ API access; check for unexpected command/env entries; network segmentation; principle of least privilege

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance Additional source 2 Additional source 3 Additional source 4
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
Agent / MCP as target
Initial access
Authenticated user access (or LANGFLOW_AUTO_LOGIN=true provides token without credentials); exploitation via POST/PATCH /api/v2/mcp/servers/{server_name} or embedded flow configs

Tooling as reported

AI products, models and artifacts

  • Langflow AI workflow platform
  • Model Context Protocol (MCP) Stdio transport

Other tooling

  • bash command execution
  • Environment variable injection (LD_PRELOAD, NODE_OPTIONS, PYTHONPATH, BASH_ENV)

Targets and reported impact

Targets / sectors
Langflow installations; multiple internet-facing vulnerable instances found; 1,423 exploitation attempts against Previdian honeypots from 27 countries
Reported scale / exposure
1,423 exploitation attempts against Previdian honeypots from 27 IPs (Sep 19-Oct 2026); 333 attempts on Oct 11 alone; first attempts Sep 19 (2+ weeks before CVE publication Oct 5); dramatic increase post-CVE
Target geography
Multiple regions

Reported attribution

Multiple attackers from 27 countries; financially motivated/opportunistic exploitation

Structured attribution

Actor
Multiple opportunistic attackers
Country
Multiple (27 countries)
Motivation
financially-motivated
Attributed by
Previdian, VulnCheck
Attribution confidence
high

Detection rules

  • Monitor MCP server API endpointsGUIDANCE

    Monitor POST/PATCH requests to /api/v2/mcp/servers/ endpoints for suspicious command parameters; alert on bash -c execution patterns, environment variable injection (LD_PRELOAD, PATH overrides), and auto-login token generation from unexpected IPs

  • File system monitoringGUIDANCE

    Monitor Langflow process for execution of child processes via bash; alert on unexpected shell command execution from Langflow worker processes

Activity timeline

First seen
2026-09-19
Last updated
2026-11-04

Updates

  • 2026-09-19 — Previdian honeypots

    First exploitation attempts observed, 2+ weeks before CVE publication

  • 2026-10-05 — GitHub Security Advisory

    CVE published

  • 2026-10-11 — Previdian, The Hacker News

    333 exploitation attempts on this day alone; public disclosure

Source defensive notes

Upgrade to Langflow 1.10.3+; disable LANGFLOW_AUTO_LOGIN; enforce strong unique passwords; review MCP server configurations; monitor /api/v2/mcp/servers/ API access; check for unexpected command/env entries; network segmentation; principle of least privilege

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0034Cost Harvesting

Exploitation of vulnerability in AI workflow platform (Langflow) via MCP server misconfiguration Source

Sources & research credit

4 sources

Research by Adam-Aghili, andifilhohub, Previdian · Langflow, Previdian

  1. GHSA-7w94-79vh-5mr2: Authenticated RCE via MCP Stdio transport github.com
  2. GHSA-w794-rj3p-xv45: OS command injection RCE via MCP stdio github.com
  3. Langflow Critical Authenticated RCE Flaw Targeted thehackernews.com
  4. VulnCheck - Pwning the AI Stack www.vulncheck.com

Two GitHub Security Advisories (GHSA-7w94-79vh-5mr2 for <1.9.0, GHSA-w794-rj3p-xv45 for <1.10.3); Previdian observed exploitation 2+ weeks before public CVE; VulnCheck analysis of AI stack vulnerabilities. Detection: monitor Langflow API /api/v2/mcp/servers/ for suspicious commands, review MCP Stdio configs, check for bash -c execution, monitor env var injection patterns (LD_PRELOAD, PATH), alert on auto-login token requests from unexpected IPs.

Record & downloads
Source record name
Langflow MCP-config RCE (GHSA-7w94-79vh-5mr2, GHSA-w794-rj3p-xv45)
Entry ID
langflow-mcp-rce-ghsa-2026
Catalog review
November 4, 2026
Category
attacks-on-ai
AI involvement confidence
confirmed