{"slug": "aispa-user-centric-system-prompt-auditing-for-large-language-model-applications", "title": "Aispa: User-Centric System Prompt Auditing for Large Language Model Applications", "summary": "A new framework called Artificial Intelligence System Prompt Assurance (AISPA) audits system prompts in AI applications, and its review of 3,249 instructions from 88 commercial AI products found that while 98.9% of products include at least one protective instruction, only 24% cover all eight user-centric dimensions, and roughly 40% contain at least one problematic instruction that works against user interests. The study, submitted to arXiv on 30 Jul 2026, highlights the need for greater transparency, standardization, and independent oversight in commercial AI system prompts.", "body_md": "# Computer Science > Artificial Intelligence\n\n[Submitted on 30 Jul 2026]\n\n# Title:AISPA: User-Centric System Prompt Auditing for Large Language Model Applications\n\n[View PDF](/pdf/2607.28617)\n\n[HTML (experimental)](https://arxiv.org/html/2607.28617v1)\n\nAbstract: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.\n\n### Current browse context:\n\ncs.AI\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/aispa-user-centric-system-prompt-auditing-for-large-language-model-applications", "canonical_source": "https://arxiv.org/abs/2607.28617", "published_at": "2026-08-01 16:19:54+00:00", "updated_at": "2026-08-01 16:53:46.575952+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-policy", "ai-ethics"], "entities": ["AISPA", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/aispa-user-centric-system-prompt-auditing-for-large-language-model-applications", "markdown": "https://wpnews.pro/news/aispa-user-centric-system-prompt-auditing-for-large-language-model-applications.md", "text": "https://wpnews.pro/news/aispa-user-centric-system-prompt-auditing-for-large-language-model-applications.txt", "jsonld": "https://wpnews.pro/news/aispa-user-centric-system-prompt-auditing-for-large-language-model-applications.jsonld"}}