---
title: "AISPA: User-Centric System Prompt Auditing for Large Language Model Applications"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.28617v1"
permalink: "https://feed.astralor.com/items/itm_c810c8dbd437114452a52e18"
published: "2026-07-30T17:58:58.000Z"
score: 76
channel: "ai"
tags: ["AISPA","AI Auditing","AI Governance","Large Language Models","System Prompt"]
---

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

## AI commentary

> This paper's value lies in bringing system prompts under the spotlight, using data to prove that the transparency gap in commercial AI is real and severe. For developers, AISPA offers a concrete checklist for self-audit; for regulators, it provides evidence to push for disclosure and standardization. Recommended for anyone focused on AI governance and product safety.

## At a glance

System prompts govern the behavior of foundation models in AI applications, yet commercial products rarely disclose them, creating a trust and accountability gap. This paper introduces AISPA, a user-centric framework that audits system prompts along eight dimensions. Analyzing 3,249 instructions from 88 commercial AI products, the authors find protective instructions are widespread but shallow: only 24% of products cover all eight dimensions, and roughly 40% contain at least one instruction that works against user interests. The study calls for greater transparency, standardization, and independent oversight of system prompts.

## Key points

- Introduces AISPA, a framework for auditing system prompts along eight user-centric dimensions
- Reviews 3,249 instructions from 88 commercial AI products, classifying each as protective or problematic
- Finds only 24% of products cover all protective dimensions, while ~40% contain at least one problematic instruction

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_c810c8dbd437114452a52e18