**HazardAuditor: From Executable Threats to Safer Computer-Use Agents**

> Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through runtime behavior rather than generated content alone. Existing guard models target static prompts and responses and are poorly suited to agent execution; existing executable safety platforms produce evaluation verdicts rather than the normalized supervision a guard mode...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：论文
- **发布时间**：2026-09-15 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.15134)