CommandCodeAI / CommandCodeAI/desktop

[Feedback]: Have proper sandboxed execution logic

未关闭
#8 0 条评论 0 个 reaction 已指派 1 人 在 GitHub 查看

@aliarain 已经在做这个了。

开始于 2026年9月7日。

enhancement
主要语言
Shell
星标
80
派生
2
PR 合并指标
30 天内没有已合并 PR

描述

What problem are you trying to solve?

The current permission settings are not sufficient for my use case. I general, the available approval modes are hard for me to understand.

What would improve it?

What I want is sandboxed execution (I am on Windows). A bit like in Codex (potentially the only app that got this right; GitHub Copilot in VS Code is not doing this, neither is Claude Code. They have a sandbox. Reads are typically allowed. Writings outside the project folder, internet access, ... requires permission. And because they have a sandbox, they can also apply this to arbitrary command executions. They can ensure that nothing can be circumvented, or hidden inside some long script, because they always limit the real effect with their sandbox.

What do you do today?

No response

Product area

None

贡献指南

这个仓库没有索引到贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。