CVE-2026-6599: Langflow Injection Vulnerability 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 range of functionalities, including model management and API integration. However, versions up to 1.8.3 have been found to be vulnerable to an injection flaw, specifically in the Model Context Protocol Configuration API, which could allow attackers to manipulate requests and potentially compromise the system.
Vulnerability Detail
A vulnerability was detected in langflow-ai langflow up to version 1.8.3. The issue lies in the function get_client_ip/install_mcp_config located in the file src/backend/base/langflow/api/v1/mcp_projects.py. By manipulating the X-Forwarded-For header, an attacker can perform an injection attack. This vulnerability can be exploited remotely, posing a risk to the integrity and confidentiality of the application. The exploit is now public, and the vendor has not responded to disclosures regarding this issue.
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
As a temporary workaround, you can implement input validation on the X-Forwarded-For header to sanitize any potentially harmful input before processing it. This can help reduce the risk of injection until a patch is applied.
Conclusion
The CVE-2026-6599 vulnerability in langflow poses a significant risk due to its potential for remote exploitation via injection attacks. Users are strongly advised to update to a patched version of the package and implement input validation as a temporary measure. Utilizing tools like Vulert can help monitor and alert for such vulnerabilities in real-time.
See every vulnerability recorded for langflow →
FAQ
The CVSS score of this vulnerability is 6.3, indicating a medium severity level.
You can use the Vulert playground at Vulert Scanner to check if your application is affected by this vulnerability without requiring any signup.
Exploitation of this vulnerability could lead to unauthorized access, data leakage, or manipulation of application behavior, potentially compromising the entire system.
Yes, any version of langflow above 1.8.3 is considered safe as it contains the necessary patches to address this vulnerability.
If immediate updates are not possible, implement input validation on the X-Forwarded-For header as a temporary workaround to mitigate risks.
Related vulnerabilities
Recent vulnerabilities recorded for langflow.
