Skill 审计报告

constraint-driven-development 审计报告.

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set up constraints" or "define our standards", when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.

已阻止 · 阻止需审查生成于 2026年10月12日启发式元数据审计
81
审计
70
信任
92
质量
72
安全性
88
维护
92
安装

OpenAgentSkill 信任评分

70
人工审查

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

91K 个 GitHub Stars

Star/Fork 活跃度

通过

100

91K 个 Star,9.8K 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

44

command execution surface, credential or environment access

安装可用性

通过

92

npx skills add addyosmani/agent-skills --skill constraint-driven-development

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/addyosmani/agent-skills/tree/main/skills/constraint-driven-development

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

8 通过 · 14 需审查

安装路径

92

通过

npx skills add addyosmani/agent-skills --skill constraint-driven-development

仓库

88

通过

https://github.com/addyosmani/agent-skills/tree/main/skills/constraint-driven-development

许可证

86

通过

MIT

维护

88

通过

距上次推送 1 个月

AI 审查

55

检查

The submitted SKILL.md excerpt is truncated mid-sentence during the interview questions, so the full instructions for Step 2 defaults and remaining process steps are not visible in this review payload.

README/SKILL.md 完整度

86

通过

Usable description available

依赖风险

44

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

36

修复

secrets or environment access, shell or command execution

Star/Fork 活跃度

100

通过

91K 个 Star,9.8K 个 Fork; 当前元数据中没有议题活跃度信息

采用度

88

通过

91K 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
  • The submitted SKILL.md excerpt is truncated mid-sentence during the interview questions, so the full instructions for Step 2 defaults and remaining process steps are not visible in this review payload.
  • No explicit security guidance is present in the excerpt about handling untrusted project files or avoiding accidental execution of malicious scripts when running the test suite or linters.
  • The floor-guard reference implementation is truncated at the import statement, making it impossible to fully verify redaction, exit-code handling, and diff-scope logic from the submitted files.
  • 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

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