This site currently shows sample data for demonstration.

Vulnerabilities

CVE-2026-33873 | BDVDB-2026-323455 Detail

langflow-ailangflow

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.

Impact#

Per CVSS v4.0: confidentiality impact high, integrity impact high, availability impact none. Attack vector: network.

Weaknesses#

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

References#

Show all 16

Exploit#

No public exploit known

History#

  1. Version 1Record published in the CVE List.
  2. Version 2Most recent update recorded in the CVE List.