Star200+

Evaluasi sebelum pemasangan

algorand-vulnerability-scanner 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.

GagalRisiko tinggiBlokir Kebijakan
78
Laporan evaluasi
82
Kepercayaan
87
Audit
55
Keamanan Agent

do not auto install

Audit score: Risky

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate algorand-vulnerability-scanner before installing it in an agent workflow
  • Keamanan
  • GitHub automation workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add trailofbits/skills --skill algorand-vulnerability-scanner

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add trailofbits/skills --skill algorand-vulnerability-scanner

Skor kepercayaan

82

Lulus

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

  • Shortlist kuat
  • 6.8K star GitHub
  • CC-BY-SA-4.0

Skor audit

87

Gagal

Berisiko

  • Permission surface may require sandboxing

Gerbang keamanan Agent

55

Gagal

This skill should not be selected by an agent without explicit human security review.

  • Do not auto-install. Inspect the source, dependencies, and permission surface first.
  • Audit risk exceeds the requested agent policy

Kejelasan lisensi

86

Lulus

CC-BY-SA-4.0

  • CC-BY-SA-4.0

Cakupan izin

50

Gagal

shell or command execution, filesystem or document access

  • Shell or command execution: high
  • 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 OpenAgentSkill engagement data yet
  • Audit risk risky exceeds max_risk=medium
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • Permission surface may require sandboxing

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

100

Diperbarui hari ini

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.