{
  "id": 18753,
  "url": "https://arxiv.org/abs/2608.11878",
  "title": "ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents",
  "summary": "Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments, stochastic LLM-based tool simulation, and predefined injection locations, limiting scalable security research across broader domains. To bridge this gap, we propose **ToolHazard**, a scalable adversarial environment synthesis framework that reduces human engineering an",
  "authors": "Yutao Mou, Pengfei Yang, Zhe Yin, Zhangchi Xue, Xiaotian Luan, Dingyao Yu",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T20:00:00.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/18753",
  "original_url": "https://arxiv.org/abs/2608.11878",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}