CVE-2024-5826: vanna vulnerable to remote code execution caused by prompt injection
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.
Published Jun 27, 2024 · Updated Jun 28, 2024
Affected packages
vanna
- Ecosystem
- PyPI
- Affected
- <= 0.6.2
- Fixed in
- No patched version yet
- Check
pip show vanna
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
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 this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology