个人 AI agent 接入了高敏感网络,暴露 agent 权限边界与部署管控的盲区
ai_agentllm事件
RT @WIRED: Sources tell WIRED that an Accenture employee’s personal Claude agent ran on a DOD network for two months before it was identified and the vulnerability could be patched. https://t.co/FF0l62ZOUX