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

arXiv: https://arxiv.org/abs/2604.04759 · HTML: https://mlsanity.com/paper/2604.04759/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 22 of 22)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [Memory Injection Attacks on LLM Agents via Query-Only Interaction](https://mlsanity.com/paper/2503.03704/) (2025)
- [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026)
- [OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety](https://mlsanity.com/paper/2507.06134/) (2025)
- [MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers](https://mlsanity.com/paper/2508.14925/) (2025)
- [Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents](https://mlsanity.com/paper/2410.13886/) (2024)
- [Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents](https://mlsanity.com/paper/2509.26354/) (2025)
- [Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections](https://mlsanity.com/paper/2602.15654/) (2026)
- ["Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors](https://mlsanity.com/paper/2509.22040/) (2025)
- [Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails](https://mlsanity.com/paper/2510.04860/) (2025)

## Built on by (most cited first, 20 of 20)

- [AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills](https://mlsanity.com/paper/2605.13940/) (2026)
- [Auditing Agent Harness Safety](https://mlsanity.com/paper/2605.14271/) (2026)
- [Towards Security-Auditable LLM Agents: A Unified Graph Representation](https://mlsanity.com/paper/2605.06812/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security](https://mlsanity.com/paper/2606.11671/) (2026)
- [OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills](https://mlsanity.com/paper/2607.20121/) (2026)
- [Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw](https://mlsanity.com/paper/2605.11047/) (2026)
- [SentGuard: Sentence-Level Streaming Guardrails for Large Language Models](https://mlsanity.com/paper/2606.02041/) (2026)
- [HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety](https://mlsanity.com/paper/2608.17597/) (2026)
- [Stateful Agent Backdoor](https://mlsanity.com/paper/2605.06158/) (2026)
- [Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation](https://mlsanity.com/paper/2605.06393/) (2026)
- [When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents](https://mlsanity.com/paper/2605.06731/) (2026)
- [Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures](https://mlsanity.com/paper/2605.25435/) (2026)
- [Triaging Threats to Specialized Guardrails](https://mlsanity.com/paper/2605.30693/) (2026)
- [Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability](https://mlsanity.com/paper/2605.07110/) (2026)
- [Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill](https://mlsanity.com/paper/2606.11007/) (2026)
- [Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents](https://mlsanity.com/paper/2607.08395/) (2026)
- [The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt](https://mlsanity.com/paper/2607.14250/) (2026)
- [Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw](https://mlsanity.com/paper/2609.22067/) (2026)
- [Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems](https://mlsanity.com/paper/2610.00371/) (2026)

## Abstract (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.