ID:12640 - Exploit for Code Injection in Langflow - CVE-2026-27966
Published: April 24, 2026
Langflow
Link to public exploit:
Vulnerability description
The vulnerability allows a remote attacker to execute arbitrary code.
The vulnerability exists due to improper control of code generation in the CSV Agent node when processing prompt input that reaches the exposed python_repl_ast tool. A remote attacker can send a specially crafted prompt to execute arbitrary code.
The issue is caused by allow_dangerous_code being hardcoded to true, which automatically exposes LangChain's Python REPL tool without a disable option.