Skill audit report

OpenSandbox Audit report.

Secure, Fast, and Extensible Sandbox runtime for AI agents.

REVIEWED · REVIEWSafe to tryGenerated Jul 30, 2026Heuristic metadata audit
93
Audit
91
Trust
100
Quality
89
Security
88
Maintain
92
Install

OpenAgentSkill Trust Score

91
Production candidate

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

100

11K GitHub stars

Stars/forks activity

PASS

92

11K stars, 946 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

88

2mo since push

License clarity

PASS

86

Apache-2.0

README/SKILL.md completeness

INFO

74

Public metadata needs stronger README/SKILL.md context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add opensandbox-group/OpenSandbox

Install command safety

PASS

92

standard package or runtime install path

Permission surface

PASS

100

no high-risk permission surface in public metadata

Repository evidence

PASS

86

https://github.com/opensandbox-group/OpenSandbox

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

11 Passed · 1 Needs review

Install path

92

PASS

npx skills add opensandbox-group/OpenSandbox

Repository

88

PASS

https://github.com/opensandbox-group/OpenSandbox

License

86

PASS

Apache-2.0

Maintenance

88

PASS

2mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

92

PASS

standard package or runtime install path

Permission surface

100

PASS

no high-risk permission surface in public metadata

Stars/forks activity

92

PASS

11K stars, 946 forks; issue activity unavailable in current metadata

Adoption

88

PASS

11K GitHub stars

Warnings

  • Documentation summary is thin

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Compare nearby options

Related skills to audit next