Laporan audit skill
lark-skill-maker Laporan audit.
创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。
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
Lulus100
17K star GitHub
Aktivitas star/fork
Lulus97
17K star dan 1.4K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
26 hari sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Info70
Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat
Risiko dependensi/runtime
Peringatan46
command execution surface, credential or environment access
Ketersediaan pemasangan
Lulus92
npx skills add larksuite/cli --skill lark-skill-maker
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Gagal24
secrets or environment access, shell or command execution
Bukti repositori
Lulus86
https://github.com/larksuite/cli/tree/main/skills/lark-skill-maker
Status peninjauan
Peringatan47.65
Persetujuan tinjauan AI belum ada
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add larksuite/cli --skill lark-skill-maker
Repositori
88
https://github.com/larksuite/cli/tree/main/skills/lark-skill-maker
Lisensi
86
MIT
Pemeliharaan
100
26 hari sejak push
Tinjauan AI
55
Review approval is missing
Kelengkapan README/SKILL.md
84
Usable description available
Risiko dependensi
46
command execution surface, credential or environment access
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
24
secrets or environment access, shell or command execution
Aktivitas star/fork
97
17K star dan 1.4K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
17K star GitHub
Peringatan
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Persetujuan tinjauan AI belum ada
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
- Review status: AI review approval is missing
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