OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

cve-lookup 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.

Perlu ditinjauRisiko sedangTinjau Kebijakan
69
Laporan evaluasi
68
Kepercayaan
74
Audit
58
Keamanan Agent

Tinjauan manual

Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate cve-lookup before installing it in an agent workflow
  • Keamanan
  • Security and compliance workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add sandbaseai/sandbase-skills --skill cve-lookup

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add sandbaseai/sandbase-skills --skill cve-lookup

Skor kepercayaan

68

Peringatan

Potentially useful, but at least one trust signal needs human inspection.

  • Tinjauan manual
  • 64 star GitHub
  • Apache-2.0

Skor audit

74

Peringatan

Perlu ditinjau

  • The API map reference is minimal and does not provide concrete parameter details, relying entirely on sandbase_describe_tool.

Gerbang keamanan Agent

58

Peringatan

Kandidat yang dapat digunakan, tetapi Agent harus menampilkan catatan izin dan audit sebelum memasang.

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • The API map reference is minimal and does not provide concrete parameter details, relying entirely on sandbase_describe_tool.

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

74

Peringatan

network or browser access, database access

  • Network access: medium
  • Database 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
  • The API map reference is minimal and does not provide concrete parameter details, relying entirely on sandbase_describe_tool.
  • No explicit error handling or rate-limit guidance is provided for the external tool calls.
  • Quality score needs review
  • GitHub adoption: 64 GitHub stars

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

76

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

Pemeliharaan terbaru

Lulus

88

2 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.