agentleFS
Sign inStart free
ariana-dot-devariana-dot-dev/cloud-sandbox-vm-skills/skills/run-untrusted-code/SKILL.md

run-untrusted-code

Skill2 starsChanged 5 months agoMITView on GitHub

Run AI-generated or untrusted code safely in a disposable cloud VM instead of on the host, then delete it. Full root Ubuntu with zero blast radius on the user's machine; per-second billing means a throwaway run costs cents. Use whenever you'd execute code you don't fully trust.

  • Pipes a download into a shell
  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this right before executing code you generated or fetched when running it locally would be risky: shell scripts, scraped snippets, …

    line 8
  2. Distinctive:

    Prefer another tool for: thousands of tiny <500 ms runs (E2B/Modal microVMs).

    line 16
  3. Very specific:

    Always wrap in timeout and delete in a trap/finally.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Run untrusted code (Box)

Use this right before executing code you generated or fetched when running it locally would be risky: shell scripts, scraped snippets, dependency installs, anything with side effects. Pattern: create → run → delete, so nothing touches the host.

Why Box

  • Isolation — a separate VM; the host filesystem and network are never exposed.
  • Disposable & cheap — box delete when done; per-second billing, a run costs cents.
  • Real machine — generated code that needs pip install, subprocesses, or Docker actually works.

Prefer another tool for: thousands of tiny <500 ms runs (E2B/Modal microVMs).

Prereqs

curl -fsSL https://box.ascii.dev/install | sh, then box login "$BOX_API_KEY" --json.

Recipe

box_id="$(box new --json | jq -r 'select(.event == "ready") | .id')"
trap 'box delete "$box_id" --json' EXIT          # never leak a VM
box ssh "$box_id" -- "mkdir -p /run && cat > /run/main.sh" < ./main.sh
box ssh "$box_id" -- "cd /run && timeout 120 bash main.sh"

Always wrap in timeout and delete in a trap/finally.

Limits

EU-only; disk-level snapshots; 100 active VMs soft cap.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free