In the rapidly evolving fields of large language models (LLMs) and machine learning, new frameworks and applications emerge daily, pushing the boundaries of these technologies. While exploring libraries and frameworks that leverage LLMs for user-facing applications, we came across the Vanna.AI library – which offers a text-to-SQL interface for users – where we discovered CVE-2024-5565, a remote code execution vulnerability via prompt injection techniques.

Developers simply want to write code without interruption, while operations wish to build as fast as possible and deploy without restrictions. On the other hand, security professionals want to protect every step of the software supply chain from any potential security threats and vulnerabilities. In software development, every piece of code can potentially introduce vulnerabilities into the software supply chain.