Laporan audit skill

dev-workflow Laporan audit.

The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.

Diblokir · BlokirPerlu ditinjauDihasilkan 11 Okt 2026Audit metadata heuristik
77
Audit
67
Kepercayaan
81
Kualitas
69
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

67
Tinjauan manual

Trust Score OpenAgentSkill

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

Adopsi GitHub

Lulus

86

5.0K star GitHub

Aktivitas star/fork

Lulus

83

5.0K star dan 823 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

Gagal

28

command execution surface, credential or environment access

Ketersediaan pemasangan

Lulus

92

npx skills add iflytek/skillhub --skill dev-workflow

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Gagal

18

secrets or environment access, shell or command execution

Bukti repositori

Lulus

86

https://github.com/iflytek/skillhub/tree/main/.agents/skills/dev-workflow

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 · 11 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add iflytek/skillhub --skill dev-workflow

Repositori

88

Lulus

https://github.com/iflytek/skillhub/tree/main/.agents/skills/dev-workflow

Lisensi

86

Lulus

Apache-2.0

Pemeliharaan

88

Lulus

1 bulan sejak push

Tinjauan AI

55

Periksa

The skill documents hardcoded staging/bootstrap credentials (admin/Admin@staging2026 and admin/ChangeMe!2026). These are likely local-only, but the SKILL.md does not explicitly warn agents to never use them outside the local/staging environment.

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

28

Perbaiki

command execution surface, credential or environment access

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

18

Perbaiki

secrets or environment access, shell or command execution

Aktivitas star/fork

83

Lulus

5.0K star dan 823 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

88

Lulus

5.0K star GitHub

Peringatan

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • The skill documents hardcoded staging/bootstrap credentials (admin/Admin@staging2026 and admin/ChangeMe!2026). These are likely local-only, but the SKILL.md does not explicitly warn agents to never use them outside the local/staging environment.
  • Some Makefile commands are destructive (dev-all-reset, db-reset, staging-down) but there is no explicit confirmation or caution step before running them.
  • 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