CVE-2026-27966
CRITICALLangflow < 1.8.0 - Remote Code Execution via CSV Agent Node
Title source: llmExploitation Summary
EIP tracks 3 public exploits for CVE-2026-27966.
PoCs published by XiaomingX, Anon-Cyber-Team, weblover12, Takahiro Yokoyama, including Metasploit module exploits/multi/http/langflow_rce_cve_2026_27966.
AI-analyzed exploit summary This repository contains a functional exploit tool for CVE-2026-27966, a critical RCE vulnerability in Langflow. The tool includes multi-threaded scanning, automatic detection, and interactive shell capabilities for remote command execution.
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.
Exploits (3)
This repository contains a functional exploit tool for CVE-2026-27966, a critical RCE vulnerability in Langflow. The tool includes multi-threaded scanning, automatic detection, and interactive shell capabilities for remote command execution.
The repository contains a functional exploit tool for CVE-2026-27966, targeting a Remote Code Execution (RCE) vulnerability in Langflow. The tool includes features for scanning, detection, and exploitation, with support for multi-threading, proxy usage, and interactive shell access.
This Metasploit module exploits CVE-2026-27966, a vulnerability in Langflow's CSV Agent node that hardcodes allow_dangerous_code=True, enabling arbitrary Python and OS command execution via prompt injection. The exploit automates the creation of a malicious flow, uploads it, and triggers execution to achieve RCE.
References (2)
Scores
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H