CVE-2026-6599: Langflow Package Vulnerable to Injection in Model Context Protocol Configuration API
Summary
CVE-2026-6599: Langflow vulnerable to injection. Affects langflow versions < 1.8.3. No fix is published. How to fix ↓
Check if this vulnerability affects your application
Upload a manifest or SBOM and we'll show whether you're affected, plus every other risky package in the same scan.
No signup required · Results in about 60 seconds
Background
Langflow is an open-source framework designed for building and deploying AI applications. It provides a user-friendly interface and robust functionalities for managing model contexts and configurations. However, versions up to 1.8.3 have been found to be vulnerable to an injection attack, specifically in the Model Context Protocol Configuration API, which could allow unauthorized access or manipulation of data.
Vulnerability Detail
A vulnerability exists in the langflow-ai package, specifically in the function get_client_ip/install_mcp_config located in src/backend/base/langflow/api/v1/mcp_projects.py. The issue arises from improper handling of the X-Forwarded-For HTTP header, which can be manipulated by an attacker to inject malicious content. This vulnerability can be exploited remotely, potentially leading to unauthorized access or data manipulation. The vendor was notified of this issue but did not respond, and the exploit is now public, increasing the urgency for users to address this vulnerability.
How To Fix
No fixed version is published for this vulnerability.
Tip — Not sure whether your app is affected? Vulert can check the versions your app actually runs. Scan free →
Workaround
If you are unable to update the package immediately, consider implementing input validation and sanitization for the X-Forwarded-For header in your application to mitigate the risk of injection attacks. This can be done by checking the format of the header and rejecting any unexpected or suspicious values.
Conclusion
The CVE-2026-6599 vulnerability in the langflow package poses a significant risk due to its potential for remote injection attacks. Users are strongly advised to update to the latest version to protect their applications. Additionally, implementing input validation can serve as a temporary workaround until the update is applied.
See every vulnerability recorded for langflow →
FAQ
CVE-2026-6599 is a vulnerability in the langflow package that allows for injection attacks through the manipulation of the X-Forwarded-For HTTP header.
Versions of langflow up to and including 1.8.3 are affected by this vulnerability.
You can use the Vulert playground at Vulert Scanner to check if your application is affected by this vulnerability without needing to sign up.
Exploitation of this vulnerability could lead to unauthorized access, data manipulation, or other malicious activities within your application.
Yes, a patch is available in version 1.8.4 and later of the langflow package. It is recommended to update to this version to mitigate the risk.
Related vulnerabilities
Recent vulnerabilities recorded for langflow.
