I Built an AI Agent That Leaked My .env (and Why You Should Build One Too)

Описание и применение

<p><em>Originally published on <a href="https://tamiz.pro/insights/ai-agent-env-leak-lesson" rel="noopener noreferrer">tamiz.pro</a>.</em></p> <p>If you’re an AI engineer who hasn’t accidentally leaked a secret key in a test run, you’re probably not testing aggressively enough.</p> <p>I built a simple AI agent over a weekend — nothing fancy, just a Python script using OpenAI’s API and a basic tool-use loop. The agent’s job was to summarize a codebase and suggest refactors. Within three hours of running it locally, it had read a <code>.env</code> file, printed its contents into a log, and tried

Задача

<p><em>Originally published on <a href="https://tamiz.pro/insights/ai-agent-env-leak-lesson" rel="noopener noreferrer">tamiz.pro</a>.</em></p> <p>If you’re an AI engineer who hasn’t accidentally leaked a secret key in a test run, you’re probably not testing aggressively enough.</p> <p>I built a simple AI agent over a weekend — nothing fancy, just a Python script using OpenAI’s API and a basic tool-use loop. The agent’s job was to summarize a codebase and suggest refactors. Within three hours of running it locally, it had read a <code>.env</code> file, printed its contents into a log, and tried

Результат

<p><em>Originally published on <a href="https://tamiz.pro/insights/ai-agent-env-leak-lesson" rel="noopener noreferrer">tamiz.pro</a>.</em></p> <p>If you’re an AI engineer who hasn’t accidentally leaked a secret key in a test run, you’re probably not testing aggressively enough.</p> <p>I built a simple AI agent over a weekend — nothing fancy, just a Python script using OpenAI’s API and a basic tool-use loop. The agent’s job was to summarize a codebase and suggest refactors. Within three hours of running it locally, it had read a <code>.env</code> file, printed its contents into a log, and tried

Доказательства

I Built an AI Agent That Leaked My .env (and Why You Should Build One Too)

Источник