Skill 审计报告
Agent Skills 审计报告.
A collection of self-contained, tested AI agent skills for Hermes Agent covering research, creative, productivity, and devops domains, designed to be portable to other agent platforms.
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
失败30
14 个 GitHub Stars
Star/Fork 活跃度
失败32
14 个 Star，1 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100
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
信息64
command execution surface, network or browser surface
安装可用性
通过92
npx skills add moonlight-lupin/agent-skills
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
警告48
shell or command execution, filesystem or document access
仓库证据
通过86
https://github.com/moonlight-lupin/agent-skills
审查状态
通过88
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 moonlight-lupin/agent-skills
仓库
88
https://github.com/moonlight-lupin/agent-skills
许可证
86
MIT
维护
88
距上次推送 1 个月
AI 审查
88
Approved with no listed issues
README/SKILL.md 完整度
100
Usable description available
依赖风险
64
command execution surface, network or browser surface
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
48
shell or command execution, filesystem or document access
Star/Fork 活跃度
32
14 个 Star，1 个 Fork; 当前元数据中没有议题活跃度信息
采用度
42
14 个 GitHub Stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
警告
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Low GitHub adoption signal
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 14 GitHub stars
- Stars/forks activity: 14 stars, 1 forks; issue activity unavailable in current metadata
- Permission surface: shell or command execution, filesystem or document access
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。
对比相近选项
下一步可审计的相关 Skill
Cli
Official Lark/Feishu CLI tool with 200+ commands and 26 AI agent skills, designed for agent-native operation and easy integration with AI runtimes.
17K Stars · 审计报告
Aaron Marketing Skills
A comprehensive set of 38 marketing skills and 5 commands for Claude Code covering SEO/GEO and influencer marketing with evaluation frameworks.
2.6K Stars · 审计报告
DashiAI Ppt Skill
An AI agent skill that generates editable web-based PPT presentations with 12 themes, 1020 layouts, and one-click PPTX export.
3.8K Stars · 审计报告