Skip to content
OpenAdvisories
Critical · 9.3 CVE-2026-33873 EUVD-2026-16815GHSA-v8hw-mh8c-jxfcPYSEC-2026-82

Langflow has Authenticated Code Execution in Agentic Assistant Validation

Published Mar 27, 2026 · Updated Apr 2, 2026 · Assigned by GitHub_M

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.

Affected products

VendorProductAffectedFixed
langflow-ai langflow < 1.9.0 —

Affected packages

EcosystemPackageAffectedFixedRecord
PyPI langflow < 1.9.0 1.9.0 GHSA-v8hw-mh8c-jxfc

Advisories 1

References