run-untrusted-code

run-untrusted-code is a skill for Claude Code, Codex from ariana-dot-dev/cloud-sandbox-vm-skills. It costs 61 tokens per session (375 once invoked), scanned C, original, MIT.

A method for running code you do not fully trust inside a temporary cloud virtual machine instead of on your computer.

In plain words
What is it for?
Use it to execute generated or scraped code that needs shell commands, installed packages, subprocesses, or Docker, then remove the temporary machine.
Why use it?
The isolated machine limits the risk from scripts, downloaded code, dependency installation, or other actions that could affect your files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to execute generated or scraped code that needs shell commands, installed packages, subprocesses, or Docker, then remove the temporary machine.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ariana-dot-dev/cloud-sandbox-vm-skills --skill run-untrusted-code
Clone the repo
git clone --depth 1 https://github.com/ariana-dot-dev/cloud-sandbox-vm-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for run-untrusted-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code/github.svg)](https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code)
Your own site
<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for run-untrusted-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/run-untrusted-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 375 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00375
Opus 5 $0.00030 $0.00187
Sonnet 5 $0.00012 $0.00075
Haiku 4.5 $0.00006 $0.00038

Measured 9d ago against content hash d06e6ce5e5d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

run-untrusted-code scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

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

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -fsSL https://box.ascii.dev/install | sh`, then `box login "$BOX_API_KEY" --json`.
skills/run-untrusted-code/SKILL.md · 36 lines

What it actually says

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 & cheapbox 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.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 36 lines · 61 tokens per session scan C d06e6ce5e5d2

Subscribe to this mod's changes

run-untrusted-code is a skill published in the GitHub repository ariana-dot-dev/cloud-sandbox-vm-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 375 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

superdesign

Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…

superdesigndev/superdesign-skill · 115 tokens

declauding

Removes LLM prose tics from drafts — staged reveals, "it's not X, it's Y", significance tags, abstraction agency, coy headers, fragment cadence, the flatter slop patterns (copula avoidance, participle tails, forced triads, chatbot residue), the flat-certainty patterns the pass itself produces (bare adverbs, juridical…

oaustegard/claude-skills · 225 tokens

image-to-svg

Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork…

oaustegard/claude-skills · 122 tokens

declaring-invariants

Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. Reports where a parametrize list, for-loop, or it.each iterates a hand-written subset of a dict/set/tuple/Enum that exists in the source, and names the members nothing covers. Use when reviewing tests, when a module…

oaustegard/claude-skills · 175 tokens

developing-preact

Specialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those involving data visualization, interactive applications, single-page apps with HTM syntax, Web Components integration, CSV/JSON…

oaustegard/claude-skills · 76 tokens

generative-thinking

Break out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, perspective shift, constraint play, or family traversal — and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations…

oaustegard/claude-skills · 152 tokens