OpenAgentSkill
GitHub200+

Evaluasi sebelum pemasangan

attack-path-stitcher 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
65
Laporan evaluasi
68
Kepercayaan
74
Audit
42
Keamanan Agent

do not auto install

Permission surface: secrets or environment access, filesystem or document access

Gerbang wajib

Pemeriksaan yang harus dilalui Agent sebelum memasang

Buka JSON

Kecocokan tugas

84

Lulus

Task wording matches this skill metadata.

  • Evaluate attack-path-stitcher before installing it in an agent workflow
  • Desain dan kreatif
  • Design and creative workflows; Claude Code teams; teams that value GitHub adoption signals

Jalur pemasangan

92

Lulus

Install handoff is available.

  • npx skills add transilienceai/communitytools --skill attack-path-stitcher

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

  • npx skills add transilienceai/communitytools --skill attack-path-stitcher

Skor kepercayaan

68

Peringatan

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

  • Tinjauan manual
  • 509 star GitHub
  • MIT

Skor audit

74

Peringatan

Perlu ditinjau

  • Permission surface may require sandboxing

Gerbang keamanan Agent

42

Peringatan

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Petunjuk izin berisiko tinggi: Secrets or environment access

Kejelasan lisensi

86

Lulus

MIT

  • MIT

Cakupan izin

34

Gagal

secrets or environment access, filesystem or document access

  • Network access: medium
  • Filesystem 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
  • The skill assumes a specific directory structure (validated/, artifacts/, findings/) which may not be portable across environments.
  • Petunjuk izin berisiko tinggi: Secrets or environment access
  • Permission surface may require sandboxing
  • The SKILL.md references reference/edge-detectors.md but does not include the full content in the excerpt; ensure the file is present in the repository.

Pemeriksaan pendukung

Sinyal kepercayaan di balik keputusan

Kelengkapan README/SKILL.md

Peringatan

76

Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat

Pemeliharaan terbaru

Lulus

88

3 bulan sejak push

Alternatif tersedia

Lulus

82

Alternative skills are available for comparison.