CVE-2024-5826

CRITICAL9.8EPSS 7.5%

vanna vulnerable to remote code execution caused by prompt injection

發布日:2024/6/27修改日:2024/6/28

描述

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.

受影響套件(1)

CVSS 分數

來源版本嚴重程度向量
osvCVSS 3.1CRITICAL9.8CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

參考連結(3)