用途分类 / 开发辅助
Karpathy Guidelines Skill 安全审计
作者说它能做什么(原文)
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
第三方安全检查结论
这次检查未发现明显风险
- 已检查文件
- 1
- 发现的风险
- 0
会不会运行危险命令?检查是否下载程序后直接运行、让他人远程控制电脑,或藏起要运行的命令。未发现风险
会不会泄露文件和密钥?检查是否发送含密码或密钥的文件,以及代码里是否直接写了密钥。未发现风险
会不会删除文件或一直在后台运行?检查是否大范围删除文件、改写磁盘,或设置自动启动。未发现风险
会不会绕过安全保护?检查是否跳过网站安全验证、开放过多文件权限,或取消操作前的确认。未发现风险
会不会误导 AI 或隐藏内容?检查工作说明是否要求 AI 忽略你的指令、干扰检查结果,或夹带看不见的文字。未发现风险
会不会偷偷改推广链接或收款方?检查是否强制替换推广链接或收款对象,同时要求隐瞒更改。未发现风险
Skill 逻辑拆解
该 Skill 是一组面向代码编写、审查和重构的行为准则;其声明目标是减少过度复杂、隐含假设和无法验证的修改。提供的完整来源仅包含文字说明,没有脚本、安装步骤、凭据请求或网络操作指令。
查看原文
---name: karpathy-guidelinesdescription: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.license: MITBefore implementing:- State your assumptions explicitly. If uncertain, ask.- If multiple interpretations exist, present them - don't pick silently.- If a simpler approach exists, say so. Push back when warranted.- If something is unclear, stop. Name what's confusing. Ask.该 Skill 指示代理只实施用户要求的功能、限制改动范围,并以测试或其他检查定义完成标准。这会影响代理的开发决策,但可见内容没有要求访问用户账户、扩大权限、泄露数据或执行持久性系统更改。
查看原文
**Minimum code that solves the problem. Nothing speculative.**- No features beyond what was asked.- No abstractions for single-use code.- No "flexibility" or "configurability" that wasn't requested.- No error handling for impossible scenarios.- If you write 200 lines and it could be 50, rewrite it.**Touch only what you must. Clean up only your own mess.**When editing existing code:- Don't "improve" adjacent code, comments, or formatting.- Don't refactor things that aren't broken.- Match existing style, even if you'd do it differently.- If you notice unrelated dead code, mention it - don't delete it.**Define success criteria. Loop until verified.**Transform tasks into verifiable goals:- "Add validation" → "Write tests for invalid inputs, then make them pass"- "Fix the bug" → "Write a test that reproduces it, then make it pass"- "Refactor X" → "Ensure tests pass before and after"从这里开始 · 工作说明SKILL.md
karpathy-guidelines文件与检查记录1 个文件
检查范围与遗漏
逐文件查看涉及的内容
下方列出本次涉及的原文范围;纳入检查不代表已查清所有问题。
SKILL.md已纳入全文
这份报告只针对上方版本。我们看了拿到的代码和说明文件,没有实际运行 Skill,也没有检查它另外安装的软件包。因此,这不是“保证安全”的承诺;换了版本或使用环境,结果也可能不同。
SKILL.md工作说明
代码和说明中提到的操作
连接外部网站
Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.- 读取了多少行
- 68
- 文件校验值(用于核对版本)
- 7e37fe1a13405c907bf022d6d89c0f4035658ba63debd14f025de769ac264426