OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

google-maps-reviews 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 google-maps-reviews before installing it in an agent workflow
  • Riset
  • Coding agents 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 google-maps-reviews

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add sandbaseai/sandbase-skills --skill google-maps-reviews

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

  • SKILL.md does not explicitly instruct the agent to treat external review content as untrusted data, so malicious reviews could attempt prompt injection.

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.
  • SKILL.md does not explicitly instruct the agent to treat external review content as untrusted data, so malicious reviews could attempt prompt injection.

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
  • SKILL.md does not explicitly instruct the agent to treat external review content as untrusted data, so malicious reviews could attempt prompt injection.
  • The referenced API map is a stub: it only lists the tool name and does not document expected parameters, output fields, or error handling.
  • No example outputs or reporting templates are provided, which may lead to inconsistent synthesized answers.
  • Quality score needs review

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.