OpenAgentSkill
GitHub200+

Skill 审计报告

openspec-propose 审计报告.

Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation. Also use when the user says "openspec propose" or "opsx propose".

实验性 · 审查需审查生成于 2026年10月13日启发式元数据审计
86
审计
80
信任
93
质量
74
安全性
100
维护
92
安装

OpenAgentSkill 信任评分

80
强候选

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

通过

100

69K 个 GitHub Stars

Star/Fork 活跃度

通过

97

69K 个 Star，4.7K 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

100

距上次推送 24 天

许可证清晰度

通过

86

MIT

README/SKILL.md 完整度

通过

94

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 Fission-AI/OpenSpec --skill openspec-propose

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

24

secrets or environment access, shell or command execution

仓库证据

通过

86

https://github.com/Fission-AI/OpenSpec/tree/bae58cf61479986431bb798acbe5a688a591c18c/skills/openspec-propose

审查状态

警告

55.88

缺少 AI 审查批准

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

8 通过 · 13 需审查

安装路径

92

通过

npx skills add Fission-AI/OpenSpec --skill openspec-propose

仓库

88

通过

https://github.com/Fission-AI/OpenSpec/tree/bae58cf61479986431bb798acbe5a688a591c18c/skills/openspec-propose

许可证

86

通过

MIT

维护

100

通过

距上次推送 24 天

AI 审查

55

检查

Review approval is missing

README/SKILL.md 完整度

94

通过

Usable description available

依赖风险

54

修复

command execution surface, credential or environment access

安装命令安全性

92

通过

标准软件包或运行时安装路径

权限范围

24

修复

secrets or environment access, shell or command execution

Star/Fork 活跃度

97

通过

69K 个 Star，4.7K 个 Fork; 当前元数据中没有议题活跃度信息

采用度

88

通过

69K 个 GitHub Stars

Financial decision safety

58

检查

Research-only use: do not treat output as financial advice or execute a position without human approval.

警告

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • Financial research output is not financial advice; require human review before any live investment decision
  • 缺少 AI 审查批准
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • Review status: AI review approval is missing

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

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

246K Stars · 审计报告

Cursor Rules

A curated collection of cursor rules for various frameworks and technologies

40K Stars · 审计报告

narrow-react-prop-types

narrow React component prop types to match live code paths

3.1K Stars · 审计报告