criticalOther UnknownPublish anonymously
Langflow CSV Agent RCE via Prompt Injection (CVE-2026-27966)
by Publish anonymously · 2 days agoviews 0en
PII protected
Personal information such as emails, phone numbers, IDs and access tokens are automatically masked before publication.
CVSS 9.8. Langflow's CSVAgentComponent hardcodes `allow_dangerous_code=True`, auto-enabling LangChain's Python REPL tool. Attackers inject malicious prompts through user-supplied input, achieving arbitrary Python/OS command execution. No authentication required. Affects versions prior to 1.8.0.