An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool._run component.
{
"source": "CPE_FIELD",
"extracted_events": [
{
"introduced": "0"
},
{
"last_affected": "0.0.232"
}
],
"cpe": "cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*"
}