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.
{
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/33xxx/CVE-2026-33873.json",
"cwe_ids": [
"CWE-94"
]
}{
"cpe": "cpe:2.3:a:langflow:langflow:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "1.9.0"
}
],
"source": [
"AFFECTED_FIELD",
"CPE_RANGE"
]
}