Laporan audit skill
hackthebox Laporan audit.
HackTheBox platform operations and automations to solve challenges, machines and capture the flags hacking competitions
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
Info76
509 star GitHub
Aktivitas star/fork
Info71
509 star dan 75 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
3 bulan sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus86
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Info64
credential or environment access, network or browser surface
Ketersediaan pemasangan
Lulus92
npx skills add transilienceai/communitytools --skill hackthebox
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Gagal34
secrets or environment access, filesystem or document access
Bukti repositori
Lulus86
https://github.com/transilienceai/communitytools/tree/main/skills/hackthebox
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 transilienceai/communitytools --skill hackthebox
Repositori
88
https://github.com/transilienceai/communitytools/tree/main/skills/hackthebox
Lisensi
86
MIT
Pemeliharaan
88
3 bulan sejak push
Tinjauan AI
55
SKILL.md is not self-contained; it references external files (workflow.md, spawning-recipes.md, etc.) that are not included in the excerpt, making it incomplete for standalone use.
Kelengkapan README/SKILL.md
86
Usable description available
Risiko dependensi
64
credential or environment access, network or browser surface
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
34
secrets or environment access, filesystem or document access
Aktivitas star/fork
71
509 star dan 75 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
509 star GitHub
Peringatan
- Permission surface may require sandboxing
- SKILL.md is not self-contained; it references external files (workflow.md, spawning-recipes.md, etc.) that are not included in the excerpt, making it incomplete for standalone use.
- Some workflow steps are vague (e.g., 'If necessary, start the machines', 'Max N concurrent agents' without defining N).
- The skill instructs using anti-bot bypass techniques (Cloudflare/Turnstile evasion) which may violate platform ToS, though it appears intended for legitimate access.
- Quality score needs review
- Permission surface needs review: secrets or environment access, filesystem or document access
- Permission surface: secrets or environment access, 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