void-box — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by the-void-ia · Agent Tool · ★ 88

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is void-box safe to install? View the security audit →

About void-box

Hardware-isolated micro-VMs for AI agents — bring any model, run any pipeline, audit every step. void-box runs each agent stage inside its own micro-VM — Claude, Codex, Ollama, or any tool you put on PATH — with hardware isolation, OTLP telemetry, and sub-second snapshot/restore. Docs · Examples · Getting Started · Architecture ⭐ Star us on GitHub — it helps the project a lot! ⭐ <img src=

agent-isolationagentic-workflowai-agentsai-runtimeclaude-codecomposable-agent-runtimedev-toolskvmobservabilityopentelemetry

Quick Facts

Stars88
Forks6
LanguageRust
CategoryAgent Tool
LicenseApache-2.0
Quality Score61.5235578108163/100
Open Issues19
Last Updated2026-09-04
Created2026-02-12
Platformsclaude-code, rust
Est. Tokens~24k

Compatible Skills

These tools work well together with void-box for enhanced workflows:

  • Symbiont — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)
  • cydonia — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (52%)
  • walrus — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (52%)

void-box alternative? Top 6 similar tools

Looking for a void-box alternative? If you're comparing void-box with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • clawmetry by vivekchand · ⭐ 421

    See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Cod

  • aura by mezmo · ⭐ 386

    AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs,

  • clay by chadbyte · ⭐ 399

    A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.

  • runtm by runtm-ai · ⭐ 297

    Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, C

  • ai-observer by tobilg · ⭐ 273

    Unified local observability for AI coding assistants

  • coop by trailofbits · ⭐ 241

    Isolated VM environment for running Claude Code and Codex

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is void-box?

void-box is Composable agent runtime with enforced isolation boundaries. It is categorized as a Agent Tool with 88 GitHub stars.

What programming language is void-box written in?

void-box is primarily written in Rust. It covers topics such as agent-isolation, agentic-workflow, ai-agents.

How do I install or use void-box?

You can find installation instructions and usage details in the void-box GitHub repository at github.com/the-void-ia/void-box. The project has 88 stars and 6 forks, indicating an active community.

What license does void-box use?

void-box is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to void-box?

The top alternatives to void-box on Agent Skills Hub include clawmetry, aura, clay. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools