Skill audit report
MedAgents audit report.
[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/abs/2311.10537
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
INFO62
350 GitHub stars
Stars/forks activity
WARN57
350 stars, 47 forks; issue activity unavailable in current metadata
Recent maintenance
FAIL22
2y since push
License clarity
WARN42
Unknown
README/SKILL.md completeness
PASS90
Metadata includes enough usage and workflow context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add gersteinlab/MedAgents
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
filesystem or document access
Repository evidence
PASS86
https://github.com/gersteinlab/MedAgents
Review status
PASS88
AI review data available
Checks
Install and adoption review
Install path
92
npx skills add gersteinlab/MedAgents
Repository
88
https://github.com/gersteinlab/MedAgents
License
45
Unknown
Maintenance
20
2y since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
90
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Install command safety
92
standard package or runtime install path
Permission surface
86
filesystem or document access
Stars/forks activity
57
350 stars, 47 forks; issue activity unavailable in current metadata
Adoption
68
350 GitHub stars
Warnings
- License is unclear
- Repository appears stale
- Repository looks stale
- Quality score needs review
- Stars/forks activity: 350 stars, 47 forks; issue activity unavailable in current metadata
- Recent maintenance: 2y since push
- License clarity: Unknown
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