Remote Code Execution via Prompt Injection in vanna-ai/vanna

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.

N/A

对生成代码的控制不恰当(代码注入)

vanna 代码注入漏洞

Vanna是Vanna公司的一个个性化 AI SQL 代理。 vanna 存在代码注入漏洞，该漏洞源于执行 LLM 生成代码缺少沙箱，导致攻击者可以操控 src/vanna/base/base.py 中的 exec函数，攻击者利用该漏洞可以在应用后端服务器上实现远程代码执行。

N/A

N/A