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.
References
Configurations
No configuration.
History
21 Nov 2024, 09:48
Type | Values Removed | Values Added |
---|---|---|
Summary |
|
|
References | () https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369 - |
27 Jun 2024, 19:25
Type | Values Removed | Values Added |
---|---|---|
New CVE |
Information
Published : 2024-06-27 19:15
Updated : 2024-11-21 09:48
NVD link : CVE-2024-5826
Mitre link : CVE-2024-5826
CVE.ORG link : CVE-2024-5826
JSON object : View
Products Affected
No product.
CWE
CWE-94
Improper Control of Generation of Code ('Code Injection')