Laporan audit skill
Bench Laporan audit.
A tool for evaluating LLMs
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adopsi GitHub
Info62
429 star GitHub
Aktivitas star/fork
Peringatan57
429 star dan 43 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Info62
7 bulan sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Info74
Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat
Risiko dependensi/runtime
Lulus90
Tidak ada petunjuk risiko dependensi besar dalam metadata publik
Ketersediaan pemasangan
Lulus92
npx skills add arthur-ai/bench
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Lulus86
Akses sistem file atau dokumen
Bukti repositori
Lulus86
https://github.com/arthur-ai/bench
Status peninjauan
Lulus88
Data tinjauan AI tersedia
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add arthur-ai/bench
Repositori
88
https://github.com/arthur-ai/bench
Lisensi
86
MIT
Pemeliharaan
62
7 bulan sejak push
Tinjauan AI
88
Approved with no listed issues
Kelengkapan README/SKILL.md
84
Usable description available
Risiko dependensi
90
Tidak ada petunjuk risiko dependensi besar dalam metadata publik
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
86
Akses sistem file atau dokumen
Aktivitas star/fork
57
429 star dan 43 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
68
429 star GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Peringatan
- Financial research output is not financial advice; require human review before any live investment decision
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Ringkasan dokumentasi masih tipis
- Stars/forks activity: 429 stars, 43 forks; issue activity unavailable in current metadata
Metode
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.
Bandingkan opsi sekitar
Skill terkait untuk diaudit berikutnya
Mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
36K Star · Laporan audit
Tensorflow
An Open Source Machine Learning Framework for Everyone
196K Star · Laporan audit
Transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
162K Star · Laporan audit