CVE-2026-33873
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.
- Affected products
- Langflow
- Langflow
- < 1.9.0
- Fix
- Available
- CVSS 3.1
- 9.9 CRITICAL
- EPSS
- 1.4% (70th percentile)
- Weakness
- CWE-94
- NVD status
- Analyzed
- Published
- 2026-03-27
No indexed exploits for CVE-2026-33873 yet
Our index is partial: it proves presence, never absence
No exploit for CVE-2026-33873 has been indexed yet. Our index is built from live traffic and upstream syncs, so this page can only say what it knows — not that no exploit exists.