HazardAuditor: From Executable Threats to Safer Computer-Use Agents
- 类型：arxiv
- 标识：2609.15134
- 链接：https://arxiv.org/abs/2609.15134
- 主分类：agent
- 形态：method
- TLDR：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 model needs to learn across heterogeneous agent frameworks. We introduce HazardAuditor, an execution-grounded framework that closes both gaps. Its infrastructure runs heterogeneous age
- 副分类：risk
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-15-agent-rag-longcontext-candidates.json