paperMay 2026Unreviewed

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Hongwei Yao, Yiming Liu, Yiling He, Bingrun Yang

Abstract

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw. DeepTrap formulates adversarial context manipulation as a black-box trajectory-level optimization problem that balances risk realization, benign-task preservation, and stealth. It combines ris

Framework mappings

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{yao2026redteaming,
  title = {{Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw}},
  author = {Hongwei Yao and Yiming Liu and Yiling He and Bingrun Yang},
  year = {2026},
  month = may,
  eprint = {2605.11047},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.11047}
}