Sandbox Execution

Use when the user asks to sandbox agent code, run untrusted code from an LLM, gVisor (runsc), Firecracker microVMs, Kata Containers, durable execution with Temporal, or sandbox snapshot and fork. Produces a sandbox config with isolation level, network and resource limits, plus a durable-execution design. Not for container image hardening (use security-container-security).

45 stars 6 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill sandbox-execution
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/harness-engineering/sandbox-execution ~/.claude/skills/sandbox-execution

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Sandbox Execution

## Purpose

This skill provides the complete architectural and operational knowledge required to
build production-grade sandboxed execution environments for AI agent systems. Agents
operating in unrestricted host environments pose catastrophic risks—arbitrary code
execution, filesystem corruption, network exfiltration, and runaway resource
consumption. This skill addresses every layer of the isolation stack: from lightweight
namespace-based sandboxing through hardware-virtualized microVMs, from ephemeral
stateless containers to durable execution frameworks that survive process crashes.

The skill covers the full lifecycle of a sandboxed agent runtime: provisioning an
isolated workspace, enforcing filesystem mount policies, applying network segmentation,
imposing CPU/memory/disk quotas, persisting and restoring agent state via snapshots,
and enabling fork-based speculative execution. It treats the sandbox itself as a
composable tool that agents can invoke, configure, and tear down programmatically.

## Core Principles

1. **Defense in Depth**: Never rely on a single isolation boundary. Layer namespace
   isolation, seccomp filters, capability dropping, and hypervisor-level separation
   to create multiple independent containment rings.

2. **Least Privilege by Default**: Every sandbox starts with zero capabilities, no
   network access, a read-only root filesystem, and no access to host devices. Access
Read the full skill on GitHub

Details

Skill name
sandbox-execution
Path
skills/harness-engineering/sandbox-execution/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Sandbox Execution skill do?

Use when the user asks to sandbox agent code, run untrusted code from an LLM, gVisor (runsc), Firecracker microVMs, Kata Containers, durable execution with Temporal, or sandbox snapshot and fork. Produces a sandbox config with isolation level, network and resource limits, plus a durable-execution design. Not for container image hardening (use security-container-security).

How do I install the Sandbox Execution skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill sandbox-execution. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Sandbox Execution popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Isv Partner Advisor

24

forcedotcom/partner-ecosystem-agentic-kit

Main entrance for Salesforce ISV partner advisory work across solution discovery, packaging, development environments, implementation, platform constraints, security readiness, and operations. Use when a partner asks for guidance and the correct specialist skill or required documentation capability must be selected.

Security

Red Team Pentest Methodology

45

j4flmao/agent-skills

Understand the theoretical frameworks of offensive security, OSINT, and attack lifecycles.

Security

Security Readiness

24

forcedotcom/partner-ecosystem-agentic-kit

Assess secure architecture, data protection, AgentExchange or AppExchange Security Review preparation, testing and scanner evidence, submission materials, and remediation readiness. Use when an ISV solution must identify security risk or prepare evidence for review without claiming guaranteed approval.

Security

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.