CVE-2026-27966

critical · 9.8

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.

9.8

CVSS

33.7%

EPSS (exploit prob.)

98th

EPSS percentile

2026-02-26

Published

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Weaknesses

CWE-94

Affected products

Vendor	Product	Affected versions
langflow	langflow	< 1.8.0

Check a specific version with /api/v1/cve/match.

References

https://github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28dc9e508
https://github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4

Query this programmatically:

curl https://evil-db.io/api/v1/cve/CVE-2026-27966