Skill of Skills
📚 resourceActivePromisingmedium

microsandbox

by superradcompany

opensource secure local-first sandboxes for ai agents

Stars

6.5k

Skill Type

🧪 Product Verification

Quality Score

107/200

License

Apache-2.0

Forks

323

Last Updated

Jun 11, 2026

Discovered

Mar 28, 2026

Validation

Passed

github.com/superradcompany/microsandbox

Quality Breakdown

107/ 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.

Trust & Verification

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.

Risk Assessment

  • Repository contains daemon/agent orchestration code (agentd) that manages sandboxed execution environments
  • Includes exec command implementation allowing arbitrary command execution within sandboxes
  • Contains network configuration and TLS implementation suggesting multi-component coordination
  • Multi-crate architecture with agent spawning/session management capabilities
  • Includes persistent configuration and state management (database layer with entity models)
  • Docker containerization and image pulling/registry integration present