GitHub Advisoryadvisory · PyPI

GHSA-rrqq-fv6m-692m vanna vulnerable to remote code execution caused by prompt injection

CRITICAL Published 2024-06-27 Modified 2024-06-28 Official page ↗
Aliases
CVE-2024-5826
Ecosystem
PyPI
Packages
vanna
Severity
Critical
CVSS vector
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-94
Reviewed
2024-06-28

Affected packages

• PyPI vanna: <= 0.6.2 (no fix yet)

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.

Related

Alias · CVE (1)

  • CVE-2024-5826 In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. vulnerability

Weakness · CWE (1)

  • CWE-94 Improper Control of Generation of Code weakness

References