Skill 审计报告
diagram-design 审计报告.
在 LazyMind 中把系统架构、流程、时序、数据模型、时间线、泳道、象限和统计图等复杂信息制作成可下载的 HTML 或独立 SVG，支持显式请求的 reveal、step 和 loop 受控动画，也可安全提取 Mermaid 与 Draw.io 后重新设计。显式提及 diagram-design、画架构图/流程图/关系图/数据图、动态展示/逐步讲解、重绘 Mermaid/Draw.io、Terminal、Sketchy 或导出 SVG 时使用；按类型读取规范与示例，执行安全、可访问性、动画和类型专项校验后发布。第四阶段仍不支持 PNG、自动品牌抓取或持久化配置。
OpenAgentSkill 信任评分
OpenAgentSkill 信任评分
Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。
GitHub 采用度
警告48
77 个 GitHub Stars
Star/Fork 活跃度
警告48
77 个 Star，49 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过88
距上次推送 1 个月
许可证清晰度
通过86
MIT
README/SKILL.md 完整度
通过86
元数据包含足够的用法与工作流上下文
依赖与运行时风险
警告54
command execution surface, credential or environment access
安装可用性
通过92
npx skills add LazyAGI/LazyMind --skill diagram-design
安装命令安全性
通过92
标准软件包或运行时安装路径
权限范围
失败36
secrets or environment access, shell or command execution
仓库证据
通过86
https://github.com/LazyAGI/LazyMind/tree/main/skills/design/diagram-design
审查状态
信息66
可用 AI 审查数据
Agent 验证结果
信息54
暂未有 Agent 结果数据
检查项
安装与采用审查
安装路径
92
npx skills add LazyAGI/LazyMind --skill diagram-design
仓库
88
https://github.com/LazyAGI/LazyMind/tree/main/skills/design/diagram-design
许可证
86
MIT
维护
88
距上次推送 1 个月
AI 审查
55
SKILL.md contains LazyMind-specific runtime workflow instructions such as get_skill, run_script, and save_chat_artifact, which may limit portability to other agent platforms; this appears intentional but should be explicitly framed.
README/SKILL.md 完整度
86
Usable description available
依赖风险
54
command execution surface, credential or environment access
安装命令安全性
92
标准软件包或运行时安装路径
权限范围
36
secrets or environment access, shell or command execution
Star/Fork 活跃度
48
77 个 Star，49 个 Fork; 当前元数据中没有议题活跃度信息
采用度
68
77 个 GitHub Stars
警告
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- SKILL.md contains LazyMind-specific runtime workflow instructions such as get_skill, run_script, and save_chat_artifact, which may limit portability to other agent platforms; this appears intentional but should be explicitly framed.
- The skill permits Google Fonts references with system font fallback. This is safe and non-executing, but it is still a network request in an otherwise offline-capable artifact; the security model should explicitly state that font loading is the only permitted remote resource.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 77 GitHub stars
- Stars/forks activity: 77 stars, 49 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
方法
本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。