Metraipolis › archive › dc_c16dd66f79bc
From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications — arXiv:2608.10281
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10281
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:18:30.916Z
- SHA-256 of the archived text
f5edbdea18ae8840d81ddac9cecb495c68a7e12a408bc40e9e843f059c41b92f- Stable URL of this page
https://metraipolis.com/documento/dc_c16dd66f79bc
How to cite
From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications — arXiv:2608.10281 — arXiv (en), https://arxiv.org/abs/2608.10281 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c16dd66f79bc (Metraipolis archive dc_c16dd66f79bc, sha256 f5edbdea18ae8840d81ddac9cecb495c68a7e12a408bc40e9e843f059c41b92f)
BibTeX
@misc{dcc16dd66f79bc,
title = {From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications — arXiv:2608.10281},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10281},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c16dd66f79bc; sha256 f5edbdea18ae8840d81ddac9cecb495c68a7e12a408bc40e9e843f059c41b92f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10281. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 web-application sinks. We systematize this attack surface through representative LLM2X variants, including LLM2SQLi, LLM2XSS, LLM2SSTI, LLM2CommandInjection, LLM2IDOR, LLM2CSRF, LLM2XXE, and LLM2SSRF. Our analysis shows that the LLM usually does not create the underlying vulnerability itself; rather, it acts as a mediation layer, and in some tool-enabled settings as a confused deputy, carrying attacker influence into components that trust model-generated or model-influenced content. As an experimental case study, we implement TicketOracle, a Flask-based LLM-integrated web application for evaluating LLM2SSRF across five attack scenarios and seven LLMs. Our results show substantial variation in susceptibility across models, suggesting that exploitation depends both on insecure application architecture and model-specific behavior. We conclude with mitigation strategies across the prompt, model, application, and network layers. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2608.10281 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T06:11:08.389Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).