---
title: "Comment by BomToBe on \"blindfold: let AI agents use credentials without seeing them\" | Hashnode"
description: "One additional containment layer for agent-authored commands is outbound network policy. The wrapper keeps secrets out of transcripts, but a command that receiv"
url: "https://hashnode.com/posts/blindfold-let-ai-agents-use-credentials-without-seeing-them/6ad1054999c1fdfa673229d7/comment/6ad1a453494d995d3d60e7bf"
---

[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)

[BomToBe](https://hashnode.com/@bomtobe-orke)

[Oct 16](https://hashnode.com/posts/blindfold-let-ai-agents-use-credentials-without-seeing-them/6ad1054999c1fdfa673229d7/comment/6ad1a453494d995d3d60e7bf)

One additional containment layer for agent-authored commands is outbound network policy. The wrapper keeps secrets out of transcripts, but a command that receives a credential can still send it to an unexpected host. A per-task allowlist of endpoints, with default-deny outbound access for the command sandbox, would limit where a leaked value can go. I work on Orke at BOMTOBE, a desktop workspace for coding-agent workflows, and this is a useful boundary to make explicit.
