Skill audit report
Open Computer Use audit report.
State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key
OpenAgentSkill Trust Score
Stars, maintenance, license, docs, dependency risk, and installability.
The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
762 GitHub stars
Recent maintenance
PASS100
2d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS90
Metadata includes enough usage and workflow context
Dependency risk
INFO64
credential or environment access, network or browser surface
Install availability
PASS92
npx skills add coasty-ai/open-computer-use
Repository evidence
PASS86
https://github.com/coasty-ai/open-computer-use
Review status
PASS88
AI review data available
Checks
Install and adoption review
Install path
92
npx skills add coasty-ai/open-computer-use
Repository
88
https://github.com/coasty-ai/open-computer-use
License
86
Apache-2.0
Maintenance
100
2d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
90
Usable description available
Dependency risk
64
credential or environment access, network or browser surface
Adoption
88
762 GitHub stars
Warnings
- Quality score needs review
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