Paper: MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents

type: paper title: "MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents" authors: Xuelong Dai, Jianyu Ma, Boyang Ma, Biwei Yan, Yijun Yang, Yue Zhang year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.20717 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-16 updated_at: 2026-06-16 status: queued relevance: high topics:

agent-evaluation
agent-safety
computer-use
rag
tool-use
workflow-agent methods:

benchmarks:

models:

datasets:

cs.CV
cs.AI
cs.CR related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 collection_queries: web-gui-agent

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

matched queries: web-gui-agent
inferred topics: agent-evaluation, agent-safety, computer-use, rag, tool-use, workflow-agent
arXiv categories: cs.CV, cs.AI, cs.CR
collection score: 14

Review Checklist

Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
Does it include a benchmark, dataset, code, or reproducible experimental setup?
Should it be promoted from queued to skimmed or summarized?

1.5 KiB Raw Blame History