Laporan audit skill

Cli Laporan audit.

Official Lark/Feishu CLI tool with 200+ commands and 26 AI agent skills, designed for agent-native operation and easy integration with AI runtimes.

Eksperimental · TinjauPerlu ditinjauDihasilkan 11 Okt 2026Audit metadata heuristik

Audit

Kepercayaan

100

Kualitas

Keamanan

Maintain

Pasang

Trust Score OpenAgentSkill

Shortlist kuat

Trust Score OpenAgentSkill

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

Adopsi GitHub

Lulus

100

17K star GitHub

Aktivitas star/fork

Lulus

17K star dan 1.3K fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

2 bulan sejak push

Kejelasan lisensi

Lulus

MIT

Kelengkapan README/SKILL.md

Lulus

100

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Gagal

command execution surface, credential or environment access

Ketersediaan pemasangan

Lulus

npx skills add larksuite/cli

Keamanan perintah pemasangan

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

Gagal

secrets or environment access, shell or command execution

Bukti repositori

Lulus

https://github.com/larksuite/cli

Status peninjauan

Lulus

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

9 Lulus · 7 Perlu ditinjau

Jalur pemasangan

Lulus

npx skills add larksuite/cli

Repositori

Lulus

https://github.com/larksuite/cli

Lisensi

Lulus

MIT

Pemeliharaan

Lulus

2 bulan sejak push

Tinjauan AI

Lulus

Approved with no listed issues

Kelengkapan README/SKILL.md

100

Lulus

Usable description available

Risiko dependensi

Perbaiki

command execution surface, credential or environment access

Keamanan perintah pemasangan

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

Perbaiki

secrets or environment access, shell or command execution

Aktivitas star/fork

Lulus

17K star dan 1.3K fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

Lulus

17K star GitHub

Peringatan

Dependency or permission surface needs review
Permission surface may require sandboxing
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

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.

Jalur pemasangan

Tinjau laporan sebelum memasang pada Agent produksi.

Tinjau sumber

Metadata yang dapat dibaca Agent

Paket keputusan mesin

JSON tersemat menyediakan tugas dan Agent yang sesuai, perintah pemasangan, skor kepercayaan, gerbang keamanan, alternatif, serta kondisi jangan gunakan untuk ditinjau Agent.

Kebijakan pemasangan: Tinjau
Agent terbaik: Go + Codex
Alternatif: 3

Buka JSON Agent

Sinyal

Skor audit: 89/100
Quality: 100/100
Trust: 85/100
Install safety: 92/100
Cakupan izin: 36/100
Pemeliharaan: 2 bulan sejak push
Event: 390 event
Star GitHub: 17K
Push terakhir: 18 Agu 2026

Keamanan Agent v2

49/100 · Hindari pemasangan otomatis

EksperimentalTinjau

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
Metadata combines secrets access with shell or command execution
Petunjuk izin berisiko tinggi: Shell or command execution, Secrets or environment access
skor keamanan Agent 49/100

Eksekusi shell atau perintah

Tinggi

Metadata skill merujuk terminal, CLI, shell, subprocess, atau alur kerja eksekusi perintah.

Akses jaringan

Sedang

Skill kemungkinan mengambil halaman jarak jauh, API, repositori, atau layanan eksternal.

Akses sistem file

Sedang

Skill dapat membaca atau menulis file proyek, dokumen, artefak yang dihasilkan, atau status workspace lokal.

Secrets or environment access

Tinggi

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

Petunjuk izin berisiko tinggi: Shell or command execution, Secrets or environment access
Dependency or permission surface needs review
Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

Kembali ke skill Alternatif Badge audit SVG

Bandingkan opsi sekitar

Cli Laporan audit.

Trust Score OpenAgentSkill

Tinjauan pemasangan dan adopsi

Skill terkait untuk diaudit berikutnya

stop-slop

unslop

Humanizer