OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

email-validator 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
68
Laporan evaluasi
66
Kepercayaan
73
Audit
57
Keamanan Agent

Tinjauan manual

Test manually in an isolated workspace and compare against safer alternatives.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

94

Lulus

Task wording matches this skill metadata.

  • Evaluate email-validator before installing it in an agent workflow
  • Riset
  • Sales and CRM 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 email-validator

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add sandbaseai/sandbase-skills --skill email-validator

Skor kepercayaan

66

Peringatan

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

  • Tinjauan manual
  • 68 star GitHub
  • Apache-2.0

Skor audit

73

Peringatan

Perlu ditinjau

  • The API map file is circular: it only says 'See sandbase_describe_tool for details' for every tool, so SKILL.md does not independently document inputs, outputs, or limitations.

Gerbang keamanan Agent

57

Peringatan

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The API map file is circular: it only says 'See sandbase_describe_tool for details' for every tool, so SKILL.md does not independently document inputs, outputs, or limitations.

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 file is circular: it only says 'See sandbase_describe_tool for details' for every tool, so SKILL.md does not independently document inputs, outputs, or limitations.
  • No explicit security guidance for handling untrusted email data or API responses as potential prompt-injection content.
  • No setup or prerequisites are documented, such as SandBase gateway availability, authentication assumptions, rate limits, or PII handling expectations.
  • No examples or expected output format are provided, which may lead to inconsistent synthesis of results.

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.