Laporan audit skill
gws-gmail Laporan audit.
Gmail: Send, read, and manage email.
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
31K star GitHub
Aktivitas star/fork
Lulus97
31K star dan 1.8K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
19 hari sejak push
Kejelasan lisensi
Lulus86
Apache-2.0
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 googleworkspace/cli --skill gws-gmail
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/googleworkspace/cli/tree/main/skills/gws-gmail
Status peninjauan
Peringatan49.45
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 googleworkspace/cli --skill gws-gmail
Repositori
88
https://github.com/googleworkspace/cli/tree/main/skills/gws-gmail
Lisensi
86
Apache-2.0
Pemeliharaan
100
19 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
31K star dan 1.8K fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
31K 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
Skill terkait untuk diaudit berikutnya
stop-slop
Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.
16K Star · Laporan audit
unslop
Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.
4.8K Star · Laporan audit
Humanizer
Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice.
37K Star · Laporan audit