Browse / Direct Prompt Injection / CVE-2023-39660
pandasai vulnerable to prompt injection
- Class
- Direct Prompt Injection (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Improper Output Handling
- Affected
- pandasai (PyPI)
- EPSS
- 1.5% chance of exploitation in 30 days
How it works, in short
Crafted prompts sent to pandasai's prompt function make the library run attacker-chosen code through the Python it generates. (Our summary, written by a model. The source text is below.)
Details
An issue in Gaberiele Venturi pandasai v.0.8.0 and before allows a remote attacker to execute arbitrary code via a crafted request to the prompt function.
References
- https://nvd.nist.gov/vuln/detail/CVE-2023-39660
- https://github.com/gventuri/pandas-ai/issues/399
- https://github.com/gventuri/pandas-ai/pull/409
- https://github.com/gventuri/pandas-ai/commit/3aac79be8fc1d18b53d66a566adddbbdd2b38ad5
- https://github.com/gventuri/pandas-ai
Source: GitHub Advisory Database, used under CC BY 4.0.