Steven Gonsalvez

Software Engineer

Running coding agents without handing them my credentials

Why CEREBRO kept it

Credential isolation for coding agents; practical agent security pattern.

The text below is an automated extraction of the article at https://blog.antonio.cx/running-agents-with-lend, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (blog.antonio.cx).

Running coding agents without handing them my credentials Table of Contents I built lend to let remote agents use tools on my laptop with my approval. Here's how it fits into my workflow. Background # I use agents heavily these days as part of my toolchain. I usually have a few going at once: Claude Code working in one repo, Codex reviewing a branch in another, and something long-running in the background. I often have them review each other's work too. None of them run on my laptop. They run on VMs I can throw away, and my laptop keeps the stuff I care about: my SSH keys, my 1Password vault,

Community take

Commenters already use proxy-based secret injection in Docker sandboxes, nono, and smolvm, but the proxy gets bypassed for Tailscale nodes.

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/agents · cerebro/signal

Also from blog.antonio.cx

Only signal from blog.antonio.cx so far.