anthropics / anthropics/claude-code

[Feature Request] Add automatic .env file protection to prevent accidental secret exposure in tool execution

未关闭
#92,487 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
area:sandbox area:security enhancement platform:macos
主要语言
Python
星标
145k
派生
23.1k
PR 合并指标
PR 指标待抓取

描述

**Bug Description**
The problem is that .env files are very commonly used in each projects and claude comes with setup that allows to read all secret keys form it. The security is put on user shoulders which creates huge human factor in terms of lack of security. There is PreToolUse hook that could be used to block but it have to be done by user manually leavig room of unsecurity for secrets huge

**Environment Info**
- Platform: darwin
- Terminal: WarpTerminal
- Version: 2.1.263
- Feedback ID: 7437f4f9-e7c8-4bad-a403-7620841ab465

**Errors**
```json
[]
```

贡献指南

这个仓库没有索引到贡献指南

调研方向

Start by locating the existing PreToolUse hook and the tool-execution path that can read project files; the issue names no specific file or test. Define the protection behavior for .env files and its validation cases before implementing, then verify that tool execution cannot expose their contents by default.

由索引模型根据 Issue 内容生成。

评估

技术栈
python
领域
cli, security
Issue 类型
功能
难度
5/5
预计耗时
一周以上
活跃度
活跃
描述清晰度
需要澄清
新手友好度
35/100

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。