AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917440399605760 |
|---|---|
| author | Zhang, Yixiang Deng, Xinhao Wu, Jiaqing Xiao, Yue Xu, Ke Li, Qi |
| author_facet | Zhang, Yixiang Deng, Xinhao Wu, Jiaqing Xiao, Yue Xu, Ke Li, Qi |
| contents | Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain confined to a single interface; instead, they can propagate across initialization, input processing, memory, decision-making, and execution, often becoming apparent only when harmful effects materialize in the environment. This paper presents AgentWard, a lifecycle-oriented, defense-in-depth architecture that systematically organizes protection across these five stages. AgentWard integrates stage-specific, heterogeneous controls with cross-layer coordination, enabling threats to be intercepted along their propagation paths while safeguarding critical assets. We detail the design rationale and architecture of five coordinated protection layers, and implement a plugin-native prototype on OpenClaw to demonstrate practical feasibility. This perspective provides a concrete blueprint for structuring runtime security controls, managing trust propagation, and enforcing execution containment in autonomous AI agents. Our code is available at https://github.com/FIND-Lab/AgentWard . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24657 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents Zhang, Yixiang Deng, Xinhao Wu, Jiaqing Xiao, Yue Xu, Ke Li, Qi Cryptography and Security Artificial Intelligence Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain confined to a single interface; instead, they can propagate across initialization, input processing, memory, decision-making, and execution, often becoming apparent only when harmful effects materialize in the environment. This paper presents AgentWard, a lifecycle-oriented, defense-in-depth architecture that systematically organizes protection across these five stages. AgentWard integrates stage-specific, heterogeneous controls with cross-layer coordination, enabling threats to be intercepted along their propagation paths while safeguarding critical assets. We detail the design rationale and architecture of five coordinated protection layers, and implement a plugin-native prototype on OpenClaw to demonstrate practical feasibility. This perspective provides a concrete blueprint for structuring runtime security controls, managing trust propagation, and enforcing execution containment in autonomous AI agents. Our code is available at https://github.com/FIND-Lab/AgentWard . |
| title | AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2604.24657 |