Laporan audit skill
VisualAgentBench Laporan audit.
Towards Large Multimodal Models as Visual Foundation Agents
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
268 star GitHub
Aktivitas star/fork
Peringatan57
268 star dan 11 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Gagal38
1 tahun sejak push
Kejelasan lisensi
Lulus86
Apache-2.0
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 THUDM/VisualAgentBench
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Lulus86
Akses sistem file atau dokumen
Bukti repositori
Lulus86
https://github.com/THUDM/VisualAgentBench
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 THUDM/VisualAgentBench
Repositori
88
https://github.com/THUDM/VisualAgentBench
Lisensi
86
Apache-2.0
Pemeliharaan
38
1 tahun 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
268 star dan 11 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
68
268 star GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Peringatan
- Repository appears stale
- Financial research output is not financial advice; require human review before any live investment decision
- Repository looks stale
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Stars/forks activity: 268 stars, 11 forks; issue activity unavailable in current metadata
- Recent maintenance: 1y since push
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
Firecrawl
The API to search, scrape, and interact with the web at scale. 🔥
139K Star · Laporan audit
Daytona
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
72K Star · Laporan audit
Ppt Master
AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images · by Hugo He
37K Star · Laporan audit