Star200+

Evaluasi sebelum pemasangan

Cariddi 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 sedangIzinkan Kebijakan
90
Laporan evaluasi
88
Kepercayaan
91
Audit
83
Keamanan Agent

Tinjauan manual

Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate Cariddi before installing it in an agent workflow
  • web-automation
  • Web scraping workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add edoardottt/cariddi

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add edoardottt/cariddi

Skor kepercayaan

88

Lulus

Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.

  • Kandidat produksi
  • 3.4K star GitHub
  • GPL-3.0

Skor audit

91

Lulus

Aman untuk dicoba

  • No major audit warning from metadata.

Gerbang keamanan Agent

83

Lulus

Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

  • Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
  • Verified listing

Kejelasan lisensi

86

Lulus

GPL-3.0

  • GPL-3.0

Cakupan izin

72

Peringatan

filesystem or document access, network or browser access

  • Network access: medium
  • Filesystem 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
  • Lingkungan berkompliansi tinggi tanpa tinjauan keamanan internal
  • No major risk signals from current metadata
  • No major trust warnings detected from available metadata
  • Production credentials, payments, or irreversible account changes without explicit human review
  • Sensitive private data before reviewing repository code, license, and permission surface

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Lulus

90

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Pemeliharaan terbaru

Lulus

88

3 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.