Laporan audit skill

agents-md Laporan audit.

AGENTS.md 거버넌스 시스템을 분석·생성하는 마스터 프롬프트. 현재 프로젝트를 분석하여 루트 AGENTS.md와 하위 AGENTS.md를 즉시 생성하고, 코드에서 찾은 팀 고유 지식(비대칭·테스트 경계·하드 제약·이중 방어·보안 경계)을 근거와 함께 Golden Rules에 반영하고, CLAUDE.md에 @AGENTS.md 링크를 추가한다. "AGENTS.md 만들어줘", "에이전트 규칙 만들어줘", "/agents-md" 호출 시 반드시 실행하라.

Eksperimental · TinjauPerlu ditinjauDihasilkan 13 Okt 2026Audit metadata heuristik
75
Audit
71
Kepercayaan
63
Kualitas
78
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

71
Tinjauan manual

Trust Score OpenAgentSkill

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

Adopsi GitHub

Peringatan

48

91 star GitHub

Aktivitas star/fork

Peringatan

48

91 star dan 28 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

88

2 bulan sejak push

Kejelasan lisensi

Lulus

86

MIT

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Lulus

82

network or browser surface

Ketersediaan pemasangan

Lulus

92

npx skills add devbrother2024/skills --skill agents-md

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Peringatan

48

shell or command execution, filesystem or document access

Bukti repositori

Lulus

86

https://github.com/devbrother2024/skills/tree/main/agents-md

Status peninjauan

Info

66

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

54

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

7 Lulus · 10 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add devbrother2024/skills --skill agents-md

Repositori

88

Lulus

https://github.com/devbrother2024/skills/tree/main/agents-md

Lisensi

86

Lulus

MIT

Pemeliharaan

88

Lulus

2 bulan sejak push

Tinjauan AI

55

Periksa

The skill instructs to overwrite existing AGENTS.md without asking for confirmation, which could be destructive if the user did not intend to replace it. However, this is a deliberate design choice for a skill explicitly invoked by the user.

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

82

Lulus

network or browser surface

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

48

Perbaiki

shell or command execution, filesystem or document access

Aktivitas star/fork

48

Perbaiki

91 star dan 28 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

68

Info

91 star GitHub

Peringatan

  • Permission surface may require sandboxing
  • The skill instructs to overwrite existing AGENTS.md without asking for confirmation, which could be destructive if the user did not intend to replace it. However, this is a deliberate design choice for a skill explicitly invoked by the user.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • GitHub adoption: 91 GitHub stars
  • Stars/forks activity: 91 stars, 28 forks; issue activity unavailable in current metadata
  • Permission surface: shell or command execution, filesystem or document access

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