From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications

Abstract

Large Language Models are increasingly integrated into web applications through chatbots, tool-calling pipelines, and agentic workflows. In these systems, user input may influence not only generated text, but also backend actions such as database queries, HTTP requests, file operations, template rendering, or API calls. This paper introduces LLM-mediated web attacks, a class of attacks in which attacker-controlled input is transformed by an LLM-integrated application and then reaches traditional

Categories

Framework mappings

Suggested from the entry's categories.

@misc{tsigkopoulos2026from,
  title = {{From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications}},
  author = {Spiros Tsigkopoulos and Christoforos Ntantogian},
  year = {2026},
  month = aug,
  eprint = {2608.10281},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.10281}
}