Laporan audit skill

emcn-design-review Laporan audit.

Review UI code for alignment with the emcn design system — components, tokens, patterns, and conventions

Diblokir · BlokirPerlu ditinjauDihasilkan 12 Okt 2026Audit metadata heuristik
81
Audit
72
Kepercayaan
88
Kualitas
75
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

72
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

30K star GitHub

Aktivitas star/fork

Lulus

97

30K star dan 3.8K fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

88

1 bulan sejak push

Kejelasan lisensi

Lulus

86

Apache-2.0

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Peringatan

54

command execution surface, credential or environment access

Ketersediaan pemasangan

Lulus

92

npx skills add simstudioai/sim --skill emcn-design-review

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Peringatan

50

secrets or environment access, shell or command execution

Bukti repositori

Lulus

86

https://github.com/simstudioai/sim/tree/main/.agents/skills/emcn-design-review

Status peninjauan

Info

66

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

54

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

8 Lulus · 12 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add simstudioai/sim --skill emcn-design-review

Repositori

88

Lulus

https://github.com/simstudioai/sim/tree/main/.agents/skills/emcn-design-review

Lisensi

86

Lulus

Apache-2.0

Pemeliharaan

88

Lulus

1 bulan sejak push

Tinjauan AI

55

Periksa

The skill defaults fix=true, which can lead an agent to modify files across a broad scope without explicit per-change confirmation. This is a safety/usability concern, especially if the user passes a wide scope like 'whole codebase'.

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

54

Perbaiki

command execution surface, credential or environment access

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

50

Perbaiki

secrets or environment access, shell or command execution

Aktivitas star/fork

97

Lulus

30K star dan 3.8K fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

88

Lulus

30K star GitHub

Peringatan

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • The skill defaults fix=true, which can lead an agent to modify files across a broad scope without explicit per-change confirmation. This is a safety/usability concern, especially if the user passes a wide scope like 'whole codebase'.
  • The SKILL.md references `.claude/rules/emcn-components.md` for the chip footer layout but does not include that file's content or describe what to do if it is missing.
  • No explicit limitation that the review is static and cannot catch runtime or visual regressions without running the app or tests.
  • 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

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