CVE-2024-12366

CRITICAL

9.8

Description

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution (RCE) instead of the intended explanation of the natural language processing by the LLM.

Details CVE

Score CVSS v3.19.8

SeveriteCRITICAL

Vecteur CVSSCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Vecteur d'attaqueNETWORK

ComplexiteLOW

Privileges requisNONE

Interaction utilisateurNONE

Publie2/11/2025

Derniere modification2/11/2025

Sourcenvd

Observations honeypot0

References

https://docs.getpanda.ai/v3/privacy-security(cret@cert.org)

https://docs.pandas-ai.com/advanced-security-agent(cret@cert.org)

https://www.kb.cert.org/vuls/id/148244(af854a3a-2127-422b-91ae-364da2661108)

Correlations IOC

Aucune correlation enregistree

This product uses data from the NVD API but is not endorsed or certified by the NVD.