xuanzhu@0.3.0
玄猪(XuanZhu)— 专为终端打造的 AI 编码 Agent
AI security review
scanned · by lpm-firewall-aiThis default creates a meaningful risk: model-requested shell commands can access the user’s environment and return results to the configured provider without an individual confirmation. The behavior is part of the user-invoked coding agent, and the inspected source does not establish a separate malicious action, so warn without blocking.