CVE-2024-5826
vanna vulnerable to remote code execution caused by prompt injection
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.
How to fix CVE-2024-5826
No fixed version has been published yet. Mitigate by removing the affected package or applying upstream guidance from the references below.
- —no fix listed
Is CVE-2024-5826 being exploited?
Moderate — EPSS is 7.5%. Track this CVE but it's not at the top of the prioritisation list.
Affected packages (1)
- from 0, <= 0.6.2
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| 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 |