Browse / Direct Prompt Injection / CVE-2024-5565
Vanna prompt injection code execution
- Class
- Direct Prompt Injection (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Improper Output Handling
- Affected
- vanna (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 15.2% chance of exploitation in 30 days
How it works, in short
User text passed to the ask method can override the prompt that generates visualisation code, so the model emits Python that the library then executes. (Our summary, written by a model. The source text is below.)
Details
The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with "visualize" set to True (default behavior) leads to remote code execution.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-5565
- https://github.com/vanna-ai/vanna
- https://research.jfrog.com/vulnerabilities/vanna-prompt-injection-rce-jfsa-2024-001034449
Source: GitHub Advisory Database, used under CC BY 4.0.