An issue in pandas-ai v.0.8.1 and before allows a remote attacker to execute arbitrary code via the _is_jailbreak function.
{
"github_reviewed_at": "2023-08-15T21:10:21Z",
"severity": "CRITICAL",
"cwe_ids": [
"CWE-74",
"CWE-94"
],
"github_reviewed": true,
"nvd_published_at": "2023-08-15T17:15:13Z"
}