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
History
No history.
MITRE Information
Status: PUBLISHED
Assigner: @huntr_ai
Published: 2024-06-27T18:40:37.441Z
Updated: 2024-06-28T15:26:27.620Z
Reserved: 2024-06-10T22:43:12.603Z
Link: CVE-2024-5826
JSON object: View
NVD Information
Status : Awaiting Analysis
Published: 2024-06-27T19:15:17.350
Modified: 2024-06-27T19:25:12.067
Link: CVE-2024-5826
JSON object: View
Redhat Information
No data.
CWE