run-untrusted-code
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.
How do I install this agent skill?
npx skills add https://github.com/ariana-dot-dev/cloud-sandbox-vm-skills --skill run-untrusted-codeIs this agent skill safe to install?
- Gen Agent Trust Hubfail
This skill poses a critical security risk by instructing the user to download and execute a script directly from an external source via shell piping. Furthermore, it creates a surface for indirect prompt injection by facilitating the execution of AI-generated or untrusted scripts in a remote environment.
- Socketwarn
1 alert: gptAnomaly
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
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 deletewhen done; $0.036/h billed per second, so a run costs cents of VM time. On the $20 plan, 200 starts a day are included; each extra start costs $0.03-$0.07. - Real machine — generated code that needs
pip install, subprocesses, or Docker actually works.
Prefer another tool for: thousands of tiny sub-second runs a day (E2B/Modal).
Prereqs
curl -fsSL https://box.ascii.dev/install | sh, then box login "$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
Runs in Germany, Finland and France (no region choice); disk-level snapshots. $20 plan: 100 boxes at once, 200 starts a day included, up to 1,200 with paid extra starts (https://docs.boat.dev/limits).
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code">View run-untrusted-code on skillZs</a>