OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

linkedin-reply-handler 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
74
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 linkedin-reply-handler before installing it in an agent workflow
  • Riset
  • Research agents workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add sergebulaev/linkedin-skills --skill linkedin-reply-handler

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add sergebulaev/linkedin-skills --skill linkedin-reply-handler

Skor kepercayaan

74

Peringatan

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

  • Shortlist kuat
  • 880 star GitHub
  • MIT

Skor audit

79

Peringatan

Perlu ditinjau

  • Fetched LinkedIn comments and post text are treated as context, but SKILL.md does not explicitly warn the agent to treat them as untrusted data rather than instructions. A malicious comment could contain prompt-injection-style text.

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.
  • Fetched LinkedIn comments and post text are treated as context, but SKILL.md does not explicitly warn the agent to treat them as untrusted data rather than instructions. A malicious comment could contain prompt-injection-style text.

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

72

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
  • Fetched LinkedIn comments and post text are treated as context, but SKILL.md does not explicitly warn the agent to treat them as untrusted data rather than instructions. A malicious comment could contain prompt-injection-style text.
  • APIFY_TOKEN is referenced as an environment variable, but there is no setup/configuration section explaining required env vars, permission scope, or what the Publora wrapper does with credentials.
  • Quality score needs review
  • Production credentials, payments, or irreversible account changes without explicit human 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.