Vulnerability · Published Feb 26, 2026 · Assigned by GitHub_M
CVE-2026-27966Langflow has Remote Code Execution in CSV Agent
Critical 9.8
In plain English
A critical-severity code injection in langflow from langflow-ai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 35.2% (higher than 98% of all known vulnerabilities). Ready-made attack tooling exists: Metasploit, public proof-of-concept code.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | langflow | no fix listed | GHSA-3645-fxcv-hqr4 |
| PyPI | langflow | no fix listed | PYSEC-2026-376 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| langflow-ai | langflow | < 1.8.0 |
Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H