Remote Code Execution via Prompt Injection in vanna-ai/vanna
Vulnerability 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.
Impact Analysis
Refer to official advisory for detailed impact metrics.
Remediation
Ensure systems are updated to the latest vendor-supplied patch levels.
Am I Vulnerable?
Launch our assessment wizard to check if your infrastructure is exposed to • CVE-2024-5826
Credits & Attribution
No credits recorded in the NVD database.
More from vanna-ai
View All →Affected Vendor
vanna-ai
View all reports →