Vulnerability Description
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain’s Python REPL tool (`python_repl_ast`). As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution (RCE). Version 1.8.0 fixes the issue.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Langflow | Langflow | < 1.8.0 |
Related Weaknesses (CWE)
References
- https://github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28Patch
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4ExploitVendor Advisory
FAQ
What is CVE-2026-27966?
CVE-2026-27966 is a vulnerability with a CVSS score of 9.8 (CRITICAL). Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes...
How severe is CVE-2026-27966?
CVE-2026-27966 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-27966?
Check the references section above for vendor advisories and patch information. Affected products include: Langflow Langflow.