@anthropic-ai/sandbox-runtime

Name: @anthropic-ai/sandbox-runtime Review
Item: @anthropic-ai/sandbox-runtime
Rating: 3.8
Author: Aaron Matthews

Skill Security Solid

Works inClaude Code

Solid Scanned — metadata only

Isolates untrusted code execution in production environments, reducing blast radius from compromised dependencies or malicious inputs while maintaining obser…

Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes

Isolate untrusted code execution from your main application infrastructure safely
Enforce resource limits on third-party scripts to prevent runaway CPU or memory consumption
Audit all system calls made by external processes for compliance and security violations

4,737 starsApache-2.0 (commercial OK)FreeQuick setup

Why it matters

Isolates untrusted code execution in production environments, reducing blast radius from compromised dependencies or malicious inputs while maintaining observability and control over system resources.

Best for

Platform teams and DevOps engineers deploying multi-tenant applications or processing untrusted third-party code.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://www.npmjs.com/package/@anthropic-ai/sandbox-runtime

By dylanc-anthropic

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

npx @anthropic-ai/sandbox-runtime

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Help me isolate untrusted code execution from my main application infrastructure safely

CostFree

Trust Signals Auto-scanned

Stars4,737Last updated2026-07-23LicenseApache-2.0 (OK for commercial use)Weekly downloads216,171Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-07-23 · scanner v1

Community Pulse New

No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 4,737 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

4/5

Versatility

5/5

Reliability

3/5

Security

3/5

Overall score3.85 / 5.00 SolidEvaluatedJul 2026

Scored from trust signals (evidence-eval-v1): 4,737 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory