Laporan audit skill
TrajectoryRL Laporan audit.
Bittensor Subnet 11 — an open skill factory that uses distributed compute and RL to produce state-of-the-art skills for AI 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
Gagal30
20 star GitHub
Aktivitas star/fork
Gagal37
20 star dan 17 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
26 hari sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus100
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Peringatan54
command execution surface, external package install surface
Ketersediaan pemasangan
Lulus92
npx skills add trajectoryRL/trajectoryRL
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Info62
shell or command execution, network or browser access
Bukti repositori
Lulus86
https://github.com/trajectoryRL/trajectoryRL
Status peninjauan
Lulus88
Data tinjauan AI tersedia
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add trajectoryRL/trajectoryRL
Repositori
88
https://github.com/trajectoryRL/trajectoryRL
Lisensi
86
MIT
Pemeliharaan
100
26 hari sejak push
Tinjauan AI
88
Approved with no listed issues
Kelengkapan README/SKILL.md
100
Usable description available
Risiko dependensi
54
command execution surface, external package install surface
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
62
shell or command execution, network or browser access
Aktivitas star/fork
37
20 star dan 17 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
42
20 star GitHub
Peringatan
- Dependency or permission surface needs review
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 20 GitHub stars
- Stars/forks activity: 20 stars, 17 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, external package install surface
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
Skill terkait untuk diaudit berikutnya
Khazix Skills
A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.
20K Star · Laporan audit
Awesome Claude Skills
A curated list of resources and tools for enhancing Claude AI workflows.
66K Star · Laporan audit