CVE-2026-33873: langflow-ai langflow Code Injection

Vulnerability summary

CVE-2026-33873 is a critical (CVSS 9.9) Code Injection vulnerability in langflow-ai langflow. EPSS estimates a 1.82% chance of exploitation in the next 30 days, higher than 78.3% of scored vulnerabilities. 1 public exploit is recorded.

Timeline

1. 27-03-2026
   PublishedVulnerability first disclosed.
2. 02-04-2026
   Last modifiedVulnerability information updated.

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.

• CWE-94Improper Control of Generation of Code ('Code Injection')The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.