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.
Use CWE-94, Langflow vendor hub and Langflow product page to widen CVE-2026-33873 into its surrounding weakness, vendor, and product context.
Compare it with CVE-2026-33017, CVE-2026-33309 and CVE-2026-27966 for nearby disclosures in the same product family.