agent/papers/items/2026-2606-30755-understanding-and-evaluating-claw-like-agent-security-through-a-computer-systems.md

Paper: Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

---

type: paper title: Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens authors: Peizhi Niu, Wenjie Qu, Shangding Gu, Tianneng Shi, Yuankai Li, Ahmad Tawaha, Hend Alzahrani, Vincent Siu, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.30755 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-29 updated_at: 2026-06-29 status: queued relevance: high topics:

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

benchmarks:

models:

datasets:

• cs.CR
• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 collection_queries: agent-safety, ai-agent

One-line Takeaway

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

Why Collected

• matched queries: agent-safety, ai-agent
• inferred topics: agent-evaluation, agent-safety, tool-use
• arXiv categories: cs.CR, cs.AI
• 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/2606.30755