Ask HN: 你如何安全地授予 LLM SSH/数据库访问权限？
10 分•作者: nico•6 个月前
我一直在使用 Claude Code 来执行 DevOps 风格的任务，例如 SSH 登录服务器、grep 日志、检查文件和查询数据库。
总的来说，它非常棒。但是，我发现自己不得不审查每一个命令，其中很多命令都是重复的。这仍然为我节省了大量时间，但很快变得有点乏味。
我希望我可以给代理一些更多的自主权。比如给它一个预先批准的命令或操作列表，它被允许通过 ssh 运行。
例如：
```
OK: ls, grep, cat, tail
Not OK: rm, mv, chmod, etc
OK: SELECT 查询
Not OK: INSERT, DELETE, DROP, TRUNCATE
```
有人成功或满意地解决了这个问题吗？
你们实际使用过哪些设置，以及你们是如何在自主性和风险之间划定界限的？
查看原文
I have been using Claude Code for DevOps style tasks like SSHing into servers, grepping logs, inspecting files, and querying databases<p>Overall it's been great. However, I find myself having to review every single command, a lot of which are repetitive. It still saves me a ton of time, but it's quickly becoming a bit tedious<p>I wish I could give the agent some more autonomy. Like giving it a list of pre-approved commands or actions that it is allowed to run over ssh<p>For example:<p><pre><code> OK: ls, grep, cat, tail
Not OK: rm, mv, chmod, etc
OK: SELECT queries
Not OK: INSERT, DELETE, DROP, TRUNCATE
</code></pre>
Has anyone successfully or satisfactorily solved this?<p>What setups have actually worked for you, and where do you draw the line between autonomy and risk?