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.
npx skills add martinholovsky/claude-skills-generator --skill sandboxinggit clone --depth 1 https://github.com/martinholovsky/claude-skills-generatorWrote 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.
[](https://agentmods.dev/skills/martinholovsky/claude-skills-generator/sandboxing)<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/sandboxing"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/sandboxing/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.
<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/sandboxing"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/sandboxing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03780 |
| Opus 5 | $0.00000 | $0.01890 |
| Sonnet 5 | $0.00000 | $0.00756 |
| Haiku 4.5 | $0.00000 | $0.00378 |
Grade A, and why
sandboxing scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
result = sandbox.run(['curl', '-s', 'http://example.com']) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
return subprocess.run( How it starts
The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandboxing Skill
name: sandboxing version: 1.0.0 domain: security/isolation risk_level: HIGH languages: [python, c, rust, go] frameworks: [seccomp, apparmor, selinux, bubblewrap] requires_security_review: true compliance: [SOC2, FedRAMP] last_updated: 2025-01-15
MANDATORY READING PROTOCOL: Before implementing sandboxing, read
references/advanced-patterns.mdfor defense-in-depth strategies andreferences/threat-model.mdfor container escape scenarios.
1. Overview
1.1 Purpose and Scope
This skill provides process isolation and sandboxing for JARVIS components:
- Linux: seccomp-bpf, AppArmor/SELinux, namespaces, cgroups
- Windows: AppContainer, Job Objects, Restricted Tokens
- macOS: sandbox-exec, App Sandbox entitlements
- Containers: Docker/Podman security contexts, Kubernetes SecurityContext
1.2 Risk Assessment
Risk Level: HIGH
Justification:
- Sandbox escapes allow full system compromise
- Misconfigurations negate all isolation benefits
- Kernel vulnerabilities bypass userspace controls
- Plugin/extension execution requires strong isolation
Attack Surface:
- Syscall filtering gaps
- Namespace escape vectors
- Capability misconfigurations
- Resource exhaustion attacks
2. Core Responsibilities
2.1 Primary Functions
- Isolate untrusted code execution from host system
- Restrict syscalls to minimum required set
- Limit resources (CPU, memory, network, filesystem)
- Enforce security policies via MAC (AppArmor/SELinux)
- Contain failures to prevent cascade effects
2.2 Core Principles
- TDD First: Write tests for sandbox restrictions before implementation
- Performance Aware: Cache permissions, lazy-load capabilities, minimize syscall overhead
- Defense in Depth: Layer multiple isolation mechanisms
- Least Privilege: Grant minimum permissions required
- Fail Secure: Default deny all access
2.3 Security Principles
- NEVER run untrusted code without syscall filtering
- NEVER grant CAP_SYS_ADMIN to sandboxed processes
- ALWAYS drop all capabilities not explicitly required
- ALWAYS use read-only root filesystem where possible
- ALWAYS apply defense-in-depth (multiple layers)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 500 lines · 0 tokens per session scan A c2a951ac5026
sandboxing is a skill published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 3,780 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…