Laporan audit skill
multi-agent-image Laporan audit.
Standalone multi-agent image generation skill for Hermes. Includes an internal design compiler, GPT-Image-2 generation via apimart.ai, case library reuse, interactive reference selection, batch workflows, and style-consistent series generation.
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
568 star GitHub
Aktivitas star/fork
Info71
568 star dan 94 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
1 bulan sejak push
Kejelasan lisensi
Lulus86
MIT
Kelengkapan README/SKILL.md
Lulus86
Metadata memuat konteks penggunaan dan alur kerja yang cukup
Risiko dependensi/runtime
Gagal36
command execution surface, credential or environment access
Ketersediaan pemasangan
Lulus92
npx skills add kangarooking/kangarooking-skills --skill multi-agent-image
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Gagal22
secrets or environment access, shell or command execution
Bukti repositori
Lulus86
https://github.com/kangarooking/kangarooking-skills/tree/main/multi-agent-image
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 kangarooking/kangarooking-skills --skill multi-agent-image
Repositori
88
https://github.com/kangarooking/kangarooking-skills/tree/main/multi-agent-image
Lisensi
86
MIT
Pemeliharaan
88
1 bulan sejak push
Tinjauan AI
55
The skill sends OPENAI_API_KEY to apimart.ai, a third-party endpoint; this should be clearly documented and users should use a dedicated/restricted key.
Kelengkapan README/SKILL.md
86
Usable description available
Risiko dependensi
36
command execution surface, credential or environment access
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
22
secrets or environment access, shell or command execution
Aktivitas star/fork
71
568 star dan 94 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
568 star GitHub
Peringatan
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The skill sends OPENAI_API_KEY to apimart.ai, a third-party endpoint; this should be clearly documented and users should use a dedicated/restricted key.
- Several reference agent files (prompt_engineer.md, qa_bot.md) still describe Stable Diffusion-era parameters such as negative prompt, cfg_scale, and sampler, which are not aligned with the current GPT-Image-2 pipeline.
- SKILL.md does not document error handling, retry/timeout behavior, or failure modes for the external generation API.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- 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
Skill terkait untuk diaudit berikutnya
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
181K Star · Laporan audit
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
95K Star · Laporan audit
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
181K Star · Laporan audit