Langflow AI pipeline RCE flaws exploited in the wild, added to CISA KEV

Multiple, disclosed Aug 2026. Leaky AI product Data exposed High

Critical unauthenticated remote code execution flaws in Langflow, a popular AI agent and pipeline builder, were exploited within about a day of disclosure and drew attacks from hundreds of IPs. Several Langflow CVEs landed on CISA's Known Exploited Vulnerabilities list, and one campaign fed Langflow access into agent-driven ransomware.

Disclosed

Aug 2026

Organization

Multiple

Vendor

Any model

Product

Langflow (open source)

Type of AI

AI-powered app

How it happened

Leaky AI product: Unsecured AI infrastructure

Harm

Data exposed

Data involved

Credentials

Reach

Many organizations

Severity

High

Model at fault

No

Status

Confirmed

Vulnerability IDs

CVE-2026-33017, CVE-2026-9198

Sources

1. https://thehackernews.com/2026/08/cisa-flags-langflow-rce-tomcat-and-n.html
2. https://www.sysdig.com/blog/cve-2026-33017-how-attackers-compromised-langflow-ai-pipelines-in-20-hours