A Large-scale Measurement of In-Page Prompt Injections Against LLM Web Agents
Open Access
- 14 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4089-4103
Abstract
No abstract availableThis publication has 19 references indexed in Scilit:
- Investigating the Impact of Dark Patterns on LLM-Based Web Agents2026
- The Odyssey of robots.txt Governance: Measuring Convention Implications of Web Bots in Large Language Model Services2025
- Benchmarking and Defending against Indirect Prompt Injection Attacks on Large Language Models2025
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Goal-Guided Generative Prompt Injection Attack on Large Language Models2024
- "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models2024
- PromptShield: Deployable Detection for Prompt Injection Attacks2024
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection2023
- PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts2023
- Detecting spam web pages through content analysis2006