Laporan audit skill
code-review Laporan audit.
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it
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
639 star GitHub
Aktivitas star/fork
Info71
639 star dan 61 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus88
1 bulan sejak push
Kejelasan lisensi
Lulus86
Apache-2.0
Kelengkapan README/SKILL.md
Lulus94
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 sandbaseai/sandbase-harness --skill code-review
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/sandbaseai/sandbase-harness/tree/main/examples/basic/skills/code-review
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 sandbaseai/sandbase-harness --skill code-review
Repositori
88
https://github.com/sandbaseai/sandbase-harness/tree/main/examples/basic/skills/code-review
Lisensi
86
Apache-2.0
Pemeliharaan
88
1 bulan sejak push
Tinjauan AI
88
Approved with no listed issues
Kelengkapan README/SKILL.md
94
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
22
secrets or environment access, shell or command execution
Aktivitas star/fork
71
639 star dan 61 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
639 star GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Peringatan
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Financial research output is not financial advice; require human review before any live investment decision.
- Permission surface needs review: secrets or environment access, shell or command execution
- 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
agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
246K Star · Laporan audit
Cursor Rules
A curated collection of cursor rules for various frameworks and technologies
40K Star · Laporan audit
narrow-react-prop-types
narrow React component prop types to match live code paths
3.1K Star · Laporan audit