Your coding agent can read .env. Here's where the API keys should live instead.

Описание и применение

<p>I gave Claude Code shell access to a side project last spring and watched it debug a failing OpenAI call the way any of us would: it ran <code>cat .env</code>. The key was now in the conversation, in the provider's logs, and in the editor's session history on disk. Nothing malicious happened. That is exactly the problem: nothing has to go wrong for a plaintext secret to travel once an agent can read files and run commands.</p> <p>I ended up building a small open-source tool to fix this for myself. This post is mostly about the <em>problem</em> and the options, because the tool only makes se

Задача

<p>I gave Claude Code shell access to a side project last spring and watched it debug a failing OpenAI call the way any of us would: it ran <code>cat .env</code>. The key was now in the conversation, in the provider's logs, and in the editor's session history on disk. Nothing malicious happened. That is exactly the problem: nothing has to go wrong for a plaintext secret to travel once an agent can read files and run commands.</p> <p>I ended up building a small open-source tool to fix this for myself. This post is mostly about the <em>problem</em> and the options, because the tool only makes se

Результат

<p>I gave Claude Code shell access to a side project last spring and watched it debug a failing OpenAI call the way any of us would: it ran <code>cat .env</code>. The key was now in the conversation, in the provider's logs, and in the editor's session history on disk. Nothing malicious happened. That is exactly the problem: nothing has to go wrong for a plaintext secret to travel once an agent can read files and run commands.</p> <p>I ended up building a small open-source tool to fix this for myself. This post is mostly about the <em>problem</em> and the options, because the tool only makes se

Доказательства

Your coding agent can read .env. Here's where the API keys should live instead.

Источник