Laporan audit skill
deeprefine Laporan audit.
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.
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
Peringatan48
92 star GitHub
Aktivitas star/fork
Peringatan43
92 star dan 7 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
2 bulan sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Info76
Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat
Risiko dependensi/runtime
Info64
command execution surface, network or browser surface
Ketersediaan pemasangan
Lulus92
npx skills add HKUST-KnowComp/DeepRefine-Skill --skill deeprefine
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Peringatan48
shell or command execution, filesystem or document access
Bukti repositori
Lulus86
https://github.com/HKUST-KnowComp/DeepRefine-Skill/blob/main/SKILL.md
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 HKUST-KnowComp/DeepRefine-Skill --skill deeprefine
Repositori
88
https://github.com/HKUST-KnowComp/DeepRefine-Skill/blob/main/SKILL.md
Lisensi
86
MIT
Pemeliharaan
88
2 bulan sejak push
Tinjauan AI
55
The SKILL.md excerpt is truncated mid-pseudocode, but the provided content is sufficient to assess the skill's design and safety.
Kelengkapan README/SKILL.md
84
Usable description available
Risiko dependensi
64
command execution surface, network or browser surface
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
48
shell or command execution, filesystem or document access
Aktivitas star/fork
43
92 star dan 7 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
68
92 star GitHub
Peringatan
- Permission surface may require sandboxing
- The SKILL.md excerpt is truncated mid-pseudocode, but the provided content is sufficient to assess the skill's design and safety.
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 92 GitHub stars
- Stars/forks activity: 92 stars, 7 forks; issue activity unavailable in current metadata
- Permission surface: shell or command execution, filesystem or document access
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