DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to check what a sandbox forwards before an agent runs with Brig

List the credentials a run forwards by name, and restrict egress if needed.

Who it is forA security-minded developer or team lead who must approve which secrets and network paths an agent can reach.

The problemIt is hard to know which credentials an agent inherits and what the sandbox can send over the network.

The outcomeYou see the forwarded credential names for a run and understand the network mode before approving the agent.

What you need first

  • A Mac with Apple silicon on macOS 14 or newer, or a Linux host on x86-64 or arm64 (Intel Macs are not supported)
  • Homebrew on macOS, or the Linux install path from brig.sh/docs/install
  • A terminal and a project folder you want the agent to work in
  • An Anthropic account if you want to run Claude Code inside the sandbox

Steps

  1. brig doctor
  2. brig info <sandbox name> (inferred, check the README)
  3. Read the network section of Brig.sh/docs/policies to confirm the egress policy you need is supported on your backend.
  4. Run brig run claude <project path> only after the forwarded names match what you approved. (inferred, check the README)

Prompt for your agent

Using the brig-sh/brig repository, check the host with `brig doctor`, then run `brig info <sandbox name>` for the sandbox you plan to use. Report the credential names it forwards and whether the network is isolated. Verify that the README says a new sandbox on hvi or Linux gets an isolated network and that Brig refuses a policy-bound run on unsupported backends.

Caveat. The sandbox still reaches the internet by default, so anything the agent can read it can also send unless you bind an egress policy on a supported backend.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page