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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (1.21%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 9.8 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 1.21% probability · 67th percentile
- CISA KEV
- Not listed
- Source
- cret@cert.org
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.