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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| Sinaptik AI | PandasAI | 2.4.0 | — |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | pandasai | <= 2.4.2 | — | GHSA-vv2h-2w3q-3fx7 |