xuanzhu@0.15.9
玄猪(XuanZhu)— 专为终端打造的 AI 编码 Agent
AI security review
scanned · by lpm-firewall-aiThe default agent configuration permits sensitive-file reads without confirmation, and the README acknowledges that such contents can reach the model provider. Because reads occur through agent tool calls rather than an automatic credential-harvesting routine, this is a serious exposure risk warranting a warning rather than a block.