Laporan audit skill
agent-customization Laporan audit.
LLM-powered injection of project context into installed agent templates via `aspens customize agents`
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adopsi GitHub
Info62
100 star GitHub
Aktivitas star/fork
Peringatan51
100 star dan 7 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
30 hari sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus86
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Peringatan54
command execution surface, credential or environment access
Ketersediaan pemasangan
Lulus92
npx skills add aspenkit/aspens --skill agent-customization
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Gagal36
secrets or environment access, shell or command execution
Bukti repositori
Lulus86
https://github.com/aspenkit/aspens/tree/main/.claude/skills/agent-customization
Status peninjauan
Info66
Data tinjauan AI tersedia
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add aspenkit/aspens --skill agent-customization
Repositori
88
https://github.com/aspenkit/aspens/tree/main/.claude/skills/agent-customization
Lisensi
86
MIT
Pemeliharaan
100
30 hari sejak push
Tinjauan AI
55
The SKILL.md does not explicitly mention prerequisites like the Claude CLI being installed or the ASPENS environment setup, which could lead to confusion for agents unfamiliar with the tool.
Kelengkapan README/SKILL.md
86
Usable description available
Risiko dependensi
54
command execution surface, credential or environment access
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
36
secrets or environment access, shell or command execution
Aktivitas star/fork
51
100 star dan 7 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
68
100 star GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Peringatan
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- The SKILL.md does not explicitly mention prerequisites like the Claude CLI being installed or the ASPENS environment setup, which could lead to confusion for agents unfamiliar with the tool.
- The 'triggers' section lists specific files and keywords, but the skill does not describe how to handle cases where those files are absent or the feature is invoked differently.
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Stars/forks activity: 100 stars, 7 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
Metode
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Bandingkan opsi sekitar