Skip to main content
← All vulnerabilities
CVE-2026-33873PYSEC-2026-82GHSA-V8HW-MH8C-JXFC

Langflow has Authenticated Code Execution in Agentic Assistant Validation

Published
Last modified
published
Not listed in CISA KEV
Fix
Fixed in 1.9.0
None on Exploit-DB, Metasploit or GitHub
  • Exploitation: none
  • Automatable: no
  • Technical impact: total

Summary

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.

Timeline

  1. CVE published
  2. CISA SSVC assessment

    Exploitation: none · Automatable: no · Technical impact: total

  3. Record last updated

Affected versions

  • langflow-ai langflow

    fixed in 1.9.0

  • langflowPyPI

    fixed in 1.9.0

References 16

GitHub · langflow-ai/langflow