dev-change-report@1.3.1
整理代码改动或技术实践成可粘贴的富文本文档,支持开发改动说明与知识分享文章两种模式
AI security review
scanned · by lpm-firewall-aiThe default postinstall hook writes this package’s own skill into a user-level agent directory and forces updates without a separate install command. The skill content matches the package’s reporting purpose, so this is an agent extension lifecycle risk rather than evidence of malicious control hijacking.