In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in src/vanna/base/base.py. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.
{
"cwe_ids": [
"CWE-94"
],
"github_reviewed": true,
"github_reviewed_at": "2024-06-28T21:08:22Z",
"nvd_published_at": "2024-06-27T19:15:17Z",
"severity": "CRITICAL"
}