CVE-2024-5826
vanna vulnerable to remote code execution caused by prompt injection
Sévérité par source
Le label propre à Trivy est CRITICAL. Critique selon GHSA.
Description
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.
Paquets affectés et versions corrigées
| Source | Paquet | Corrigé en |
|---|---|---|
| pip::GitHub Security Advisory pip | vanna | pas de correctif indiqué |