Laporan audit skill
manuscript-manager Laporan audit.
Motor de estado. Rastreia tudo entre sessões — capítulos, scores, decisões, handoffs. Sem isso, o contexto se perde e o pipeline desmorona. Usar no INÍCIO e FIM de toda sessão de trabalho no livro. É a peça mais crítica do sistema.
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
115 star GitHub
Aktivitas star/fork
Peringatan57
115 star dan 38 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
1 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
Lulus90
Tidak ada petunjuk risiko dependensi besar dalam metadata publik
Ketersediaan pemasangan
Lulus92
npx skills add felipelobomotta-blip/book-genesis-studio --skill manuscript-manager
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Lulus100
Tidak ada cakupan izin berisiko tinggi dalam metadata publik
Bukti repositori
Lulus86
https://github.com/felipelobomotta-blip/book-genesis-studio/tree/master/skills/manuscript-manager
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 felipelobomotta-blip/book-genesis-studio --skill manuscript-manager
Repositori
88
https://github.com/felipelobomotta-blip/book-genesis-studio/tree/master/skills/manuscript-manager
Lisensi
86
MIT
Pemeliharaan
88
1 bulan sejak push
Tinjauan AI
55
SKILL.md does not explicitly instruct the agent to treat PROJECT_STATE.yaml and other project files as untrusted data, leaving room for prompt injection if a state file contains instructions.
Kelengkapan README/SKILL.md
84
Usable description available
Risiko dependensi
90
Tidak ada petunjuk risiko dependensi besar dalam metadata publik
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
100
Tidak ada cakupan izin berisiko tinggi dalam metadata publik
Aktivitas star/fork
57
115 star dan 38 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
68
115 star GitHub
Peringatan
- SKILL.md does not explicitly instruct the agent to treat PROJECT_STATE.yaml and other project files as untrusted data, leaving room for prompt injection if a state file contains instructions.
- Safe operating boundaries are not fully explicit: the skill mentions creating missing folders and updating PROJECT_STATE.yaml, but does not clearly prohibit destructive actions like deleting or rewriting chapter files.
- The consistency check for word count and chapter status is underspecified; different agents may count words or infer status differently.
- Quality score needs review
- Stars/forks activity: 115 stars, 38 forks; issue activity unavailable in current metadata
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