CVE-2026-27966

CRITICAL

9.8

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.

CVE Details

CVSS v3.1 Score9.8

SeverityCRITICAL

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

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published2/26/2026

Last Modified2/28/2026

Sourcenvd

Honeypot Sightings0

Affected Products

langflow:langflow

Weaknesses (CWE)

CWE-94

References

https://github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28dc9e508(security-advisories@github.com)

https://github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.