INCIDENT MAP

Browse / Direct Prompt Injection / CVE-2023-39660

pandasai vulnerable to prompt injection

CVE-2023-39660 ยท 2023-08-21 high

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

Source: GitHub Advisory Database, used under CC BY 4.0.