Laporan audit skill
no-eval-skill Laporan audit.
A skill with no eval.yaml for testing discovery behavior.
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
Lulus94
5.3K star GitHub
Aktivitas star/fork
Lulus88
5.3K star dan 403 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
1 bulan sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Gagal36
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 dotnet/skills --skill no-eval-skill
Keamanan perintah pemasangan
Info68
dynamic command execution, standard package or runtime install path
Cakupan izin
Lulus86
Akses sistem file atau dokumen
Bukti repositori
Lulus86
https://github.com/dotnet/skills/tree/main/eng/skill-validator/tests/fixtures/no-eval-skill
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 dotnet/skills --skill no-eval-skill
Repositori
88
https://github.com/dotnet/skills/tree/main/eng/skill-validator/tests/fixtures/no-eval-skill
Lisensi
86
MIT
Pemeliharaan
88
1 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
68
dynamic command execution, standard package or runtime install path
Cakupan izin
86
Akses sistem file atau dokumen
Aktivitas star/fork
88
5.3K star dan 403 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
5.3K star GitHub
Peringatan
- Quality score needs review
- Ringkasan dokumentasi masih tipis
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
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
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
169K Star · Laporan audit
Appsmith
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
41K Star · Laporan audit
Implement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
176K Star · Laporan audit