A new framework, Artificial Intelligence System Prompt Assurance (AISPA), has been introduced to address the lack of transparency and accountability in system prompts used in large language model applications. System prompts, which are instructions configured by developers, play a crucial role in governing the behavior of foundation models in AI applications, but are often not disclosed to the public or regulators. AISPA aims to bridge this trust gap by providing a user-centric approach to auditing system prompts, allowing for more transparent and accountable AI systems1. The framework is particularly relevant in the context of commercial AI products, where system prompts are widely used but rarely scrutinized. As large language models continue to be developed and deployed, the security implications of these systems will become increasingly important. The introduction of AISPA is a significant step towards ensuring the trustworthiness of AI systems, and its impact will be felt as the technology continues to evolve.