CVE-2026-27966 Langflow has Remote Code Execution in CSV Agent
Attackers can execute arbitrary code on Langflow servers via prompt injection in the CSV Agent node due to hardcoded dangerous code settings.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-27966?
CVE-2026-27966 is a critical code injection vulnerability in Langflow Langflow, published on 26 Feb 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
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.
Weakness: CWE-94
Which versions are affected by CVE-2026-27966?
3 open source packages ship an affected version, including langflow. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
langflow PyPI | All versions to 1.8.0rc2 | None |
langflow PyPI | All versions to 1.8.0rc2 | None |
langflow PyPI | All versions to 1.8.0rc2 | None |
Products include Langflow Langflow.
How do I fix CVE-2026-27966?
No fix has been published for CVE-2026-27966 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-27966 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-27966 exists.
Public exploit code: 1 Metasploit module and 2 proofs of concept on GitHub.
Other vulnerabilities in Langflow Langflow
Sources
Also known as GHSA-3645-fxcv-hqr4, PYSEC-2026-376.