AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

2026-07-30

AI Summary

This study addresses the lack of transparency and oversight in system prompts deployed by commercial large language models, which undermines user trust and accountability. The authors propose AISPA, a novel framework for systematically auditing system prompts from the user perspective. They develop an eight-dimensional evaluation schema and conduct a large-scale empirical analysis of 3,249 instructions across 88 commercial products, combining qualitative categorization with quantitative metrics. Findings reveal substantial heterogeneity in prompt design across products: while 98.9% include protective instructions, only 24% comprehensively cover all eight dimensions, and 40% still contain content potentially detrimental to user interests. These results underscore the urgent need for transparent prompt disclosure mechanisms and independent regulatory oversight.

Abstract

System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intelligence System Prompt Assurance (AISPA), a user-centric framework for systematically auditing system prompts in AI systems. AISPA examines specific parts of a system prompt and evaluates them along eight dimensions that matter to users. We then use this framework to review 3,249 instructions from system prompts in 88 commercial AI products, classifying each instruction as either protective (of users) or problematic. Our audit surfaces four core findings. First, system prompt design varies substantially across products and developers, with some organizations averaging over 60 protective instructions per product while others average fewer than 5. Second, protective instructions are widely adopted but shallow in scope: 98.9% of products contain at least one, yet only 24% cover all eight dimensions of the AISPA taxonomy. Third, system prompts have grown steadily longer and more protective of users, suggesting that user protection is becoming a more visible concern in commercial prompt design. Fourth, despite this progress, problematic instructions remain pervasive: roughly 40% of products contain at least one instruction that works against user interests, and protective and problematic instructions frequently coexist within the same prompt. Our findings highlight the need for greater transparency, standardization, and independent oversight for system prompts in commercial AI products.

Problem

• system prompts
• trust gap
• accountability
• AI transparency
• commercial AI products

Innovation

• system prompt auditing
• user-centric AI
• AISPA
• foundation model governance
• AI transparency