Browse / Improper Output Handling / CVE-2024-5826
vanna vulnerable to remote code execution caused by prompt injection
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Direct Prompt Injection
- Affected
- vanna (PyPI)
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.9% chance of exploitation in 30 days
How it works, in short
Prompts steer the model into generating code that vanna executes without a sandbox, letting the attacker run commands on the backend server. (Our summary, written by a model. The source text is below.)
Details
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
- https://nvd.nist.gov/vuln/detail/CVE-2024-5826
- https://github.com/vanna-ai/vanna
- https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369
Source: GitHub Advisory Database, used under CC BY 4.0.