PandasAI interactive prompt function Remote Code Execution (RCE)
GHSA-vv2h-2w3q-3fx7 · CVE-2024-12366 · PYSEC-2026-448
Published · Modified
AI SAST
Find this class of vulnerability in your own code
Corgea's AI-native static analysis detects vulnerabilities like this one across your repositories, ranks them by exploitability, and returns review-ready fixes.
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. The security controls of PandasAI (2.4.3 and earlier) fail to distinguish between legitimate and malicious inputs, allowing the attackers to manipulate the system into executing untrusted code, leading to untrusted code execution (RCE), system compromise, or pivoting attacks on connected services.
References
- ADVISORY https://nvd.nist.gov/vuln/detail/CVE-2024-12366
- WEB https://docs.getpanda.ai/v3/privacy-security
- WEB https://docs.pandas-ai.com/advanced-security-agent
- WEB https://github.com/pypa/advisory-database/tree/main/vulns/pandasai/PYSEC-2026-448.yaml
- PACKAGE https://github.com/sinaptik-ai/pandas-ai
- WEB https://pypi.org/project/pandasai
- WEB https://www.kb.cert.org/vuls/id/148244
Ready to move
Start Securing
Free, no credit card | First findings in minutes