ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

2026-03-16

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Multiagent Systems: Agent CommunicationCognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved informationResponsible Web: Machine-in-the-loop, human agency and autonomyGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored. In particular, OpenClaw, an open-source platform with over 40{,}000 active instances, has stood out recently with its persistent configurations, tool-execution privileges, and cross-platform messaging capabilities. In this work, we present ClawWorm, the first self-replicating worm attack against a production-scale agent framework, achieving a fully autonomous infection cycle initiated by a single message: the worm first hijacks the victim's core configuration to establish persistent presence across session restarts, then executes an arbitrary payload upon each reboot, and finally propagates itself to every newly encountered peer without further attacker intervention. We evaluate the attack on a controlled testbed across three distinct infection vectors and three payload types, demonstrating high success rates in end-to-end infection, sustained multi-hop propagation, and payload independence from the worm mechanism. We analyse the architectural root causes underlying these vulnerabilities and propose defence strategies targeting each identified trust boundary. Code and samples will be released upon completion of responsible disclosure.

Similar Papers

The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies

2024-07-28arXiv.orgCitations: 62