홈 › Papers

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

2026-04-06 · Zijun Wang, Haoqin Tu, Letian Zhang, Hardy Chen, Juncheng Wu, Xiangyan Liu, Zhenlong Yuan, Tianyu Pang, Michael Qizhe Shieh, Fengze Liu, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie arxiv

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose a substantial attack surface that existing sandboxed evaluations fail to capture. To address this gap, we present the first real-world safety evaluation of OpenClaw and introduce the CIK taxonomy, which unifies an agent's persistent state into three dimensions, i.e., Capability, Identity, and Knowledge, for safety analysis. Our evaluations cover 12 attack scenarios on a live OpenClaw instance across four backbone models (Claude Sonnet 4.5, Opus 4.6, Gemini 3.1 Pro, and GPT-5.4). The results show that poisoning any single CIK dimension increases the average attack success rate from 24.6% to 64-74%, with even the most robust model exhibiting more than a threefold increase over its baseline vulnerability. We further assess three CIK-aligned defense strategies alongside a file-protection mechanism; however, the strongest defense still yields a 63.8% success rate under Capability-targeted attacks, while file protection blocks 97% of malicious injections but also prevents legitimate updates. Taken together, these findings show that the vulnerabilities are inherent to the agent architecture, necessitating more systematic safeguards to secure personal AI agents. Our project page is https://ucsc-vlaa.github.io/CIK-Bench.

📄 PDF Abstract BibTeX arXiv:2604.04759

Code (0)

등록된 구현이 없습니다.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

2026-07-22 · Or Zion Eliav, Eyal Lenga, Shir Bernstien, Yisroel Mirsky arxiv

Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissan…

Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis

2025-08-07 · Kunyu Feng, Yue Ma, Xinhua Zhang, Boshi Liu 외 arxiv

With the growing demands of AI-generated content (AIGC), the need for high-quality, diverse, and scalable data has become increasingly crucial. However, collecting large-scale real-world data remains costly and time-cons…

WorldClaw: Agentic 3D Open-World Generation at Scale

2026-08-05 · Chunchao Guo, Jinpeng Li, Yang Li, Zilong Huang hf

Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, and explicit assets suitable for downstrea…

Scene Generation

Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

2025-10-18 · Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen, Benjamin Plaut arxiv

As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While uncertainty quantification is well-studied for single-turn tasks, multi…

Text Generation

Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems

2026-01-26 · Jusheng Zhang, Yijia Fan, Kaitong Cai, Jing Yang 외 arxiv

Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry often spirals costs. Existing paradigms, su…