LLMHigh
CVE-2024-12366: PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrar…
- Occurred
- Feb 11, 2025
- Published
- Feb 11, 2025
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2024-12366
- cvss:CRITICAL
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Prompt injection vulnerability in PandasAI allows arbitrary Python code execution, posing significant security risk.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8