---
title: "Comment by netproxy on \"blindfold: let AI agents use credentials without seeing them\" | Hashnode"
description: "This is the cleanest take on the problem I've seen. Most advice stops at \"don't paste secrets into the agent\", which ignores how agents actually work — they nee"
url: "https://hashnode.com/posts/blindfold-let-ai-agents-use-credentials-without-seeing-them/6ad1054999c1fdfa673229d7/comment/6ad15a32808637a8688cf600"
---

[Discussion](https://hashnode.com/posts/blindfold-let-ai-agents-use-credentials-without-seeing-them/6ad1054999c1fdfa673229d7)

Comment [blindfold: let AI agents use credentials without seeing them](https://hashnode.com/posts/blindfold-let-ai-agents-use-credentials-without-seeing-them/6ad1054999c1fdfa673229d7)

[netproxy](https://hashnode.com/@argumentmoney8117)

[Oct 15](https://hashnode.com/posts/blindfold-let-ai-agents-use-credentials-without-seeing-them/6ad1054999c1fdfa673229d7/comment/6ad15a32808637a8688cf600)

This is the cleanest take on the problem I've seen. Most advice stops at "don't paste secrets into the agent", which ignores how agents actually work — they need to make real API calls to do anything useful. Injecting short-lived credentials as env vars per invocation feels like the right granularity, and I'm glad you called out the redaction-in-prompt issue: once a credential value is visible in context, the transcript leak is already baked in. Curious how it handles tools that echo config back in their output — that feels like the next leak vector worth covering.
