OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

web3-bug-classes 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
67
Laporan evaluasi
71
Kepercayaan
77
Audit
41
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 web3-bug-classes before installing it in an agent workflow
  • Keamanan
  • Security and compliance workflows; Claude Code teams; builders willing to evaluate younger projects

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add Awarexone/web3-bug-bounty-hunting-ai-skills --skill web3-bug-classes

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add Awarexone/web3-bug-bounty-hunting-ai-skills --skill web3-bug-classes

Skor kepercayaan

71

Peringatan

Potentially useful, but at least one trust signal needs human inspection.

  • Tinjauan manual
  • 156 star GitHub
  • MIT

Skor audit

77

Gagal

Berisiko

  • Dependency or permission surface needs review

Gerbang keamanan Agent

41

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

MIT

  • MIT

Cakupan izin

50

Gagal

secrets or environment access, shell or command execution

  • Shell or command execution: high
  • Network access: medium
  • Secrets or environment access: high

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
  • No explicit limitations or scope boundaries are stated in the SKILL.md, which could lead to misuse if an agent assumes it covers all possible vulnerabilities beyond the 10 listed classes.
  • Audit risk risky exceeds max_risk=medium
  • Petunjuk izin berisiko tinggi: Shell or command execution, Secrets or environment access
  • Dependency or permission surface 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

100

21 hari sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.