agent/papers/items/2026-2606-22864-when-auc-0-998-is-not-enough-a-candidate-evaluation-protocol-for-hidden-state-pr.md

Paper: When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents

---

type: paper title: "When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents" authors: Yanhang Li, Zhichao Fan, Zexin Zhuang year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.22864 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-22 updated_at: 2026-06-22 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• tool-use methods:

benchmarks:

models:

datasets:

• cs.LG 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, tool-use
• arXiv categories: cs.LG
• 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?

Links

• arXiv: https://arxiv.org/abs/2606.22864