Skills
.Work. You
Rest

sage-sandbox-security

Community

Hardening Sage sandbox for safer code execution.

Software Engineering#security#auditing#Rust#policy#sandbox#OS-isolation#command-validation
Authormajiayu000
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Sage requires safe and auditable command execution. This Skill provides a structured guide to implement and reason about a multi-layered sandbox to protect the host from untrusted tasks.

Core Features & Use Cases

  • Command validation to prevent injection and unsafe commands.
  • Path policy to guard sensitive files and enforce access controls.
  • OS-level sandboxing (macOS sandbox-exec and Linux seccomp) for strong isolation.
  • Violation tracking and auditing with severity levels for ongoing security posture.

Quick Start

Configure the sandbox with a balanced default, then progressively tighten it in Strict mode for high-safety tasks. Example: let sandbox = SandboxBuilder::new().enabled(true).mode(SandboxMode::Strict).working_dir(PathBuf::from("/tmp/sage/work")).build()?; Use the sandbox to execute trusted tasks inside an isolated environment.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: sage-sandbox-security
Download link: https://github.com/majiayu000/sage/archive/main.zip#sage-sandbox-security

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.