paperAugust 2026Unreviewed

ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

Kai Wang, Zeming Wei, BiaoJie Zeng, Chang Jin, An Wang, Xiaokun Luan, Zhixiao Lin, Jingjing Qu, Xia Hu, Xingcheng Xu

Abstract

As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action consequence--while a denied dangerous objective can reapp

Cite

@misc{wang2026clawsentry,
  title = {{ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents}},
  author = {Kai Wang and Zeming Wei and BiaoJie Zeng and Chang Jin and An Wang and Xiaokun Luan and Zhixiao Lin and Jingjing Qu and Xia Hu and Xingcheng Xu},
  year = {2026},
  month = aug,
  eprint = {2608.21101},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.21101}
}