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.
Use CWE-94, Langflow vendor hub and Langflow product page to widen CVE-2026-27966 into its surrounding weakness, vendor, and product context.
Compare it with CVE-2026-33017, CVE-2026-33309 and CVE-2026-33873 for nearby disclosures in the same product family.