CVE-2026-27966

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.

CVSS v3.1

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

CVSS v3.1

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

EPSS

33.69% chance of exploitation in the next 30 days, 98th percentile

Published

2026-02-26

Updated

2026-02-28

Proof-of-concept exploits (1)

• Anon-Cyber-Team/CVE-2026-27966--RCE-in-Langflow2★ · 2026-03-06

Metasploit modules (1)

• rapid7/metasploit-framework/blob/master/modules/exploits/multi/http/langflow_rce_cve_2026…

References

• CVE Record
• NVD entry

Related

• CVE-2026-27964
• CVE-2026-27971
• CVE-2026-27962
• CVE-2026-27977
• CVE-2026-2796
• CVE-2026-27978