CVE-2024-5826
vanna vulnerable to remote code execution caused by prompt injection
9.8
CRITICAL
CVSS 3.1
EPSS 0.88%
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.
如何修補 CVE-2024-5826
目前尚未發布修補版本。可考慮移除受影響套件,或參考下方連結中的上游建議。
- —未列出修補版本
CVE-2024-5826 正在被利用嗎?
低 — EPSS 為 0.9%,目前沒有觀察到大規模利用活動。
受影響套件(1)
- from 0, <= 0.6.2
CVSS 分數
| 來源 | 版本 | 嚴重程度 | 向量 |
|---|---|---|---|
| osv | CVSS 3.1 | CRITICAL9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |