CVE-2026-33873

9.9 CRITICAL
Published: March 27, 2026 Modified: April 03, 2026
View on NVD

Description

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

Login to generate AI explanation

CVSS v3.x Details

0.0 Low Medium High Critical 10.0
Vector String
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory
https://github.com/langflow-ai/langflow/security/advisories/GHSA-v8hw-mh8c-jxfc
Source: security-advisories@github.com
Exploit Mitigation Vendor Advisory

16 reference(s) from NVD

Quick Stats

CVSS v3 Score
9.9 / 10.0
EPSS (Exploit Probability)
0.1%
30th percentile
Exploitation Status
Not in CISA KEV

Weaknesses (CWE)

Affected Vendors

langflow