OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

url 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
67
Laporan evaluasi
72
Kepercayaan
77
Audit
49
Keamanan Agent

do not auto install

Task fit: Task fit is weak; compare alternatives before selecting.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

58

Gagal

Task fit is weak; compare alternatives before selecting.

  • Evaluate url before installing it in an agent workflow
  • automation
  • Web scraping workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add axoviq-ai/synthadoc --skill url

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add axoviq-ai/synthadoc --skill url

Skor kepercayaan

72

Peringatan

Good trust signals with a few areas worth checking before rollout.

  • Shortlist kuat
  • 1.2K star GitHub
  • AGPL-3.0-or-later

Skor audit

77

Peringatan

Perlu ditinjau

  • Dependency or permission surface needs review

Gerbang keamanan Agent

49

Peringatan

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah

Kejelasan lisensi

86

Lulus

AGPL-3.0-or-later

  • AGPL-3.0-or-later

Cakupan izin

48

Gagal

shell or command execution, filesystem or document access

  • Shell or command execution: high
  • Network access: medium
  • Filesystem 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
  • production agents without a repository review
  • No explicit handling of non-HTTP schemes (e.g., file://) in redirects, which could pose SSRF risk if used in an untrusted environment.
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • Dependency or permission surface needs review
  • Permission surface may require sandboxing

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

70

Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat

Pemeliharaan terbaru

Lulus

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.