Injection Vulnerability in langflow-ai Model Context Protocol Configuration API
CVE-2026-6599

5.3MEDIUM

Key Information:

Vendor: Langflow-ai
Status: Langflow
Vendor: CVE Published:; 20 April 2026

🔔 Create Langflow-ai Vulnerability Alert

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-6599?

A vulnerability exists in langflow-ai's Model Context Protocol Configuration API, specifically in the get_client_ip/install_mcp_config function located in src/backend/base/langflow/api/v1/mcp_projects.py. By manipulating the X-Forwarded-For argument, an attacker can execute an injection attack. The exploit, which can be initiated remotely, has been made public. Despite early notification to the vendor, no response has been received regarding this security issue.

Affected Version(s)

langflow 1.8.0

langflow 1.8.1

langflow 1.8.2

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2026-6599 - Proof of Concept