CVE-2026-33873 PUBLISHED

Langflow has Authenticated Code Execution in Agentic Assistant Validation

Assigner: GitHub_M
Reserved: 24.03.2026 Published: 27.03.2026 Updated: 27.03.2026

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.

Metrics

CVSS Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N
CVSS Score: 9.3

Product Status

Vendor langflow-ai
Product langflow
Versions
  • Version < 1.9.0 is affected

References

Problem Types

  • CWE-94: Improper Control of Generation of Code ('Code Injection') CWE