OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

reverse-engineer-anything Laporan evaluasi.

Keputusan pemasangan yang dapat dibaca mesin untuk Agent: kecocokan tugas, Trust Score, Audit Score, keamanan pemasangan, cakupan izin, dan rencana validasi konkret sebelum skill menyentuh workspace.

GagalRisiko tinggiBlokir Kebijakan
74
Laporan evaluasi
77
Kepercayaan
84
Audit
36
Keamanan Agent

do not auto install

Permission surface: secrets or environment access, shell or command execution

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate reverse-engineer-anything before installing it in an agent workflow
  • developer-tools
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add https://github.com/morluto/rea/tree/7c207c79512f6baa70f4ed9d7d5334ab2d62f3ac/.agents/skills/reverse-engineer-anything --skill "reverse-engineer-anything"

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add https://github.com/morluto/rea/tree/7c207c79512f6baa70f4ed9d7d5334ab2d62f3ac/.agents/skills/reverse-engineer-anything --skill "reverse-engineer-anything"

Skor kepercayaan

77

Peringatan

Published by the site owner. Automated review approval and runtime verification are not implied.

  • Owner published · Review required
  • 94K star GitHub
  • MIT

Skor audit

84

Peringatan

Perlu ditinjau

  • Dependency or permission surface needs review

Gerbang keamanan Agent

36

Peringatan

Published by the site owner. Automated review approval and runtime verification are not implied.

  • Inspect the pinned source and approve installation explicitly in an isolated workspace.
  • Published by the site owner. Automated review approval and runtime verification are not implied.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

18

Gagal

secrets or environment access, shell or command execution

  • Shell or command execution: high
  • Browser automation: medium
  • Network access: medium

Rencana validasi

Langkah Agent berikutnya

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Jangan gunakan ketika

Kondisi yang membutuhkan skill lain

  • Tim yang membutuhkan SLA dengan dukungan vendor
  • Lingkungan berkompliansi tinggi tanpa tinjauan keamanan internal
  • Published by the site owner. Automated review approval and runtime verification are not implied.
  • Petunjuk izin berisiko tinggi: Shell or command execution, Secrets or environment access
  • Dependency or permission surface needs review
  • Permission surface may require sandboxing

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Lulus

100

1 hari sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.