- CVSS
- CRITICAL · 9.8 v3.0 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Published
- 2024-06-27
- Weakness
- CWE-94
- Source
- nvd.nist.gov/vuln/detail/CVE-2024-5826
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.
References
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-5826 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.