# ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

arXiv: https://arxiv.org/abs/2603.24414 · HTML: https://mlsanity.com/paper/2603.24414/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 25 Mar 2026.

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

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [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)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents](https://mlsanity.com/paper/2406.03007/) (2024)
- [From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows](https://mlsanity.com/paper/2506.23260/) (2025)
- [Memory Poisoning Attack and Defense on Memory Based LLM-Agents](https://mlsanity.com/paper/2601.05504/) (2026)
- [From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent](https://mlsanity.com/paper/2602.08412/) (2026)
- [Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw](https://mlsanity.com/paper/2603.10387/) (2026)
- [Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats](https://mlsanity.com/paper/2603.11619/) (2026)
- [The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey](https://mlsanity.com/paper/2603.11088/) (2026)
- [Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw](https://mlsanity.com/paper/2603.12644/) (2026)
- [From Storage to Steering: Memory Control Flow Attacks on LLM Agents](https://mlsanity.com/paper/2603.15125/) (2026)
- [AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems](https://mlsanity.com/paper/2603.15727/) (2026)
- [A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)](https://mlsanity.com/paper/2602.14364/) (2026)
- [OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models](https://mlsanity.com/paper/2510.19169/) (2025)
- [Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection](https://mlsanity.com/paper/2603.13424/) (2026)

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

- [A Systematic Security Evaluation of OpenClaw and Its Variants](https://mlsanity.com/paper/2604.03131/) (2026)
- [Auditing Agent Harness Safety](https://mlsanity.com/paper/2605.14271/) (2026)
- [AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security](https://mlsanity.com/paper/2605.29801/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection](https://mlsanity.com/paper/2605.17986/) (2026)
- [Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS](https://mlsanity.com/paper/2605.25389/) (2026)
- [SUDP: Secret-Use Delegation Protocol for Agentic Systems](https://mlsanity.com/paper/2604.24920/) (2026)
- [TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning](https://mlsanity.com/paper/2605.10038/) (2026)
- [Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw](https://mlsanity.com/paper/2605.11047/) (2026)
- [ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents](https://mlsanity.com/paper/2605.22321/) (2026)
- [CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution](https://mlsanity.com/paper/2604.16762/) (2026)
- [From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers](https://mlsanity.com/paper/2604.18652/) (2026)
- [Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures](https://mlsanity.com/paper/2605.25435/) (2026)
- [SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents](https://mlsanity.com/paper/2606.02302/) (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)
- [Hybrid Analysis for Secure MCP Tool Use in LLM Agents](https://mlsanity.com/paper/2607.25297/) (2026)
- [Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents](https://mlsanity.com/paper/2608.12977/) (2026)
- [A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors](https://mlsanity.com/paper/2609.03884/) (2026)
- [Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems](https://mlsanity.com/paper/2610.00371/) (2026)

## Abstract (arXiv)

OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell command execution. However, these broad operational privileges introduce critical security vulnerabilities, transforming model errors into tangible system-level threats such as sensitive data leakage, privilege escalation, and malicious third-party skill execution. Existing security measures for the OpenClaw ecosystem remain highly fragmented, addressing only isolated stages of the agent lifecycle rather than providing holistic protection. To bridge this gap, we present ClawKeeper, a real-time security framework that integrates multi-dimensional protection mechanisms across three complementary architectural layers. (1) Skill-based protection operates at the instruction level, injecting structured security policies directly into the agent context to enforce environment-specific constraints and cross-platform boundaries. (2) Plugin-based protection serves as an internal runtime enforcer, providing configuration hardening, proactive threat detection, and continuous behavioral monitoring throughout the execution pipeline. (3) Watcher-based protection introduces a novel, decoupled system-level security middleware that continuously verifies agent state evolution. It enables real-time execution intervention without coupling to the agent's internal logic, supporting operations such as halting high-risk actions or enforcing human confirmation. We argue that this Watcher paradigm holds strong potential to serve as a foundational building block for securing next-generation autonomous agent systems. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and robustness of ClawKeeper across diverse threat scenarios. We release our code.