Prompt injection was initially framed as the large language model (LLM) analogue of SQL injection. However, over the past three years, attacks labeled as prompt injection have evolved from isolated input-manipulation exploits into multistep attack mechanisms that resemble malware. In this paper, we argue that prompt injections evolved into promptware, a new class of malware execution mechanism triggered through prompts engineered to exploit an application's LLM. We introduce a seven-stage promptware kill chain: Initial Access (prompt injection), Privilege Escalation (jailbreaking), Reconnaissance, Persistence (memory and retrieval poisoning), Command and Control, Lateral Movement, and Actions on Objective. We analyze thirty-six prominent studies and real-world incidents affecting production LLM systems and show that at least twenty-one documented attacks that traverse four or more stages of this kill chain, demonstrating that the threat model is not merely theoretical. We discuss the need for a defense-in-depth approach that addresses all stages of the promptware life cycle and review relevant countermeasures for each step. By moving the conversation from prompt injection to a promptware kill chain, our work provides analytical clarity, enables structured risk assessment, and lays a foundation for systematic security engineering of LLM-based systems.

翻译：提示注入最初被视作大型语言模型（LLM）领域的SQL注入类比。然而在过去三年间，被归类为提示注入的攻击已从孤立的输入操纵漏洞利用，演变为类似恶意软件的多阶段攻击机制。本文提出，提示注入已发展为提示软件——一种通过精心设计的提示触发、利用应用程序LLM的新型恶意软件执行机制。我们提出了一个七阶段提示软件杀伤链：初始访问（提示注入）、权限提升（越狱）、侦察、持久化（记忆与检索污染）、命令与控制、横向移动及目标行动。通过分析影响生产环境LLM系统的三十六项重要研究及真实案例，我们证明至少有二十一起已记录的攻击贯穿了该杀伤链的四个或更多阶段，表明该威胁模型并非仅停留在理论层面。我们探讨了需要采用纵深防御策略来应对提示软件生命周期的所有阶段，并回顾了各步骤的相应防护措施。通过将讨论范畴从提示注入扩展至提示软件杀伤链，本研究提供了清晰的分析框架，支持结构化风险评估，并为基于LLM系统的系统性安全工程奠定了基础。