Cloudflare Sandbox
ListedSafely test code & configurations in a Jackspace-managed Cloudflare sandbox environment without impacting production.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add jackspace/claudeskillz --skill cloudflare-sandbox -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
jackspace
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.
No pipe-to-shell installers: failed
Runs code fetched at install time in 2 places.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
What it found
- skills/cloudflare-sandbox/SKILL.json:20npm install straight from a URL
"Complete Setup Checklist": "- [ ] `npm install @cloudflare/sandbox@latest`\r\n- [ ] Add `nodejs_compat` to compatibility_flags\r\n- [ ] Add containers configu… - skills/cloudflare-sandbox/SKILL.json:22npm install straight from a URL
"Core API Reference": "### Getting a Sandbox\r\n\r\n```typescript\r\nimport { getSandbox } from '@cloudflare/sandbox';\r\n\r\nconst sandbox = getSandbox(env.Sa…
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
Pinned to a commit: passed
Scanned jackspace/claudeskillz at aef4e299d1.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- aef4e299d1
- Scanned
- 3 files, 1,211 lines
About this skill
What it does
This skill allows AI agents to interact with and test applications within a Cloudflare Sandbox environment. It provides a secure, isolated space for experimentation without impacting live production systems. The agent can execute commands, deploy code snippets, and observe results within the sandbox.
When to use it
- Testing new features: Deploy and test experimental features in an isolated environment before pushing them to production.
- Debugging issues: Replicate and debug problems in a controlled setting without affecting live users.
- Evaluating third-party integrations: Safely assess the impact of integrating external services or code into your Cloudflare infrastructure.
- Learning Cloudflare features: Experiment with different Cloudflare functionalities and configurations in a risk-free environment.
Key capabilities
- Sandbox deployment and management
- Command execution within the sandbox
- Code snippet deployment
- Result observation
Example prompts
- "Deploy this Python script to my Cloudflare Sandbox."
- "Run
ls -linside the Cloudflare Sandbox environment." - "What's the output of the 'hello world' application running in the sandbox?"
Tips & gotchas
- Requires a working Cloudflare account and familiarity with basic command-line operations.
- Sandbox resources are limited; complex deployments may require adjustments or alternative approaches.