⌨️ cli toolActivePromisingmedium

zerobox

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.

Stars

646

Skill Type

⚙️ Infrastructure Operations

Quality Score

102/200

License

Apache-2.0

Forks

Last Updated

Jun 11, 2026

Discovered

Apr 6, 2026

Validation

Passed

github.com/afshinm/zerobox

Quality Breakdown

102/ 200

Content Signals

○Gotchas/Edge Cases+40

✓Progressive Disclosure+30

○Trigger Description+20

○Verification/Safety+20

✓Code Examples+15

○Composability+15

Repo Health

✓Recent Activity+15

✓Scripts/Automation+10

✓Real Usage (Issues)+10

✓Single Responsibility+10

✓Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Tool provides cross-platform process sandboxing with command execution capabilities - inherently executes arbitrary commands within sandbox constraints
File system access control module allows reading/writing to specified paths, creating potential for unintended data access if misconfigured
Network filtering based on domains could be bypassed or misconfigured, allowing unintended external communication
Multiple SDKs (Rust, TypeScript, Python) increase surface area for integration into AI agent workflows with execution capabilities
Examples directory includes 'ai-agent-sandboxed' which suggests integration with AI agents that could autonomously execute commands
Credential injection mechanism, while designed for security, handles sensitive API keys and could leak them if sandbox escapes occur