CVE-2024-12366

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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTNIST
9.8 CRITICAL
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
certccCNA
---
---
CVEADP
---
---
CISA-ADPADP
9.8 CRITICAL
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Awaiting analysis
This vulnerability is currently awaiting analysis.
Base Score
CVSS 3.x
EPSS Score
Percentile: 56%
References
https://docs.getpanda.ai/v3/privacy-security
https://docs.pandas-ai.com/advanced-security-agent
https://www.kb.cert.org/vuls/id/148244