Laporan audit skill
Skill Eval Harness Laporan audit.
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
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
Peringatan48
63 star GitHub
Aktivitas star/fork
Peringatan43
63 star dan 5 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
22 hari sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus90
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Peringatan54
command execution surface, credential or environment access
Ketersediaan pemasangan
Lulus92
npx skills add adewale/skill-eval-harness
Keamanan perintah pemasangan
Info68
dynamic command execution, standard package or runtime install path
Cakupan izin
Gagal36
secrets or environment access, shell or command execution
Bukti repositori
Lulus86
https://github.com/adewale/skill-eval-harness
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 adewale/skill-eval-harness
Repositori
88
https://github.com/adewale/skill-eval-harness
Lisensi
86
MIT
Pemeliharaan
100
22 hari sejak push
Tinjauan AI
88
Approved with no listed issues
Kelengkapan README/SKILL.md
90
Usable description available
Risiko dependensi
54
command execution surface, credential or environment access
Keamanan perintah pemasangan
68
dynamic command execution, standard package or runtime install path
Cakupan izin
36
secrets or environment access, shell or command execution
Aktivitas star/fork
43
63 star dan 5 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
68
63 star GitHub
Peringatan
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 63 GitHub stars
- Stars/forks activity: 63 stars, 5 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
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
Khazix Skills
A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.
20K Star · Laporan audit
Awesome Claude Skills
A curated list of resources and tools for enhancing Claude AI workflows.
66K Star · Laporan audit