Skill audit report
Open AgentRL audit report.
[ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings
OpenAgentSkill Trust Score
Stars, maintenance, license, docs, install safety, permission surface, 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
548 GitHub stars
Stars/forks activity
INFO71
548 stars, 56 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
5d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS90
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO72
command execution surface
Install availability
PASS92
npx skills add Gen-Verse/Open-AgentRL
Install command safety
PASS92
standard package or runtime install path
Permission surface
INFO76
shell or command execution
Repository evidence
PASS86
https://github.com/Gen-Verse/Open-AgentRL
Review status
PASS88
AI review data available
Checks
Install and adoption review
Install path
92
npx skills add Gen-Verse/Open-AgentRL
Repository
88
https://github.com/Gen-Verse/Open-AgentRL
License
86
Apache-2.0
Maintenance
100
5d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
90
Usable description available
Dependency risk
72
command execution surface
Install command safety
92
standard package or runtime install path
Permission surface
76
shell or command execution
Stars/forks activity
71
548 stars, 56 forks; issue activity unavailable in current metadata
Adoption
88
548 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