OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

automation-sandbox-post-copy-config-generate 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
73
Laporan evaluasi
73
Kepercayaan
79
Audit
59
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

84

Lulus

Task wording matches this skill metadata.

  • Evaluate automation-sandbox-post-copy-config-generate before installing it in an agent workflow
  • Desain dan kreatif
  • Document processing workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add forcedotcom/sf-skills --skill automation-sandbox-post-copy-config-generate

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add forcedotcom/sf-skills --skill automation-sandbox-post-copy-config-generate

Skor kepercayaan

73

Peringatan

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

  • Shortlist kuat
  • 964 star GitHub
  • Apache-2.0

Skor audit

79

Peringatan

Perlu ditinjau

  • Permission surface may require sandboxing

Gerbang keamanan Agent

59

Peringatan

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

  • Memerlukan persetujuan manusia sebelum memasang ke workspace nyata.
  • Permission surface may require sandboxing

Kejelasan lisensi

86

Lulus

Apache-2.0

  • Apache-2.0

Cakupan izin

60

Peringatan

filesystem or document access, network or browser access

  • Network access: medium
  • Filesystem 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 skill processes untrusted document content (PDF, DOCX, Markdown, images) but does not explicitly instruct the agent to treat that content strictly as data and ignore any instructions embedded within it. A malicious SOP could attempt prompt injection.
  • Permission surface may require sandboxing
  • The SKILL.md excerpt appears truncated in the provided review material at the workflow section; verify that the full workflow is present and complete in the repository.
  • Quality score needs review

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

88

1 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.