Laporan audit skill

audit Laporan audit.

Whole-repo audits in eight modes. Codebase — merged structural + correctness audit, should this exist AND does it do what it promises. Triggers "nuclear review", "code judo", "whole codebase review", "should this exist", "adversarial audit", "fable audit", "correctness audit", "expectation gaps". Docs/Process — doc drift, walkable journeys. Triggers "audit the docs", "doc drift", "process audit", "walk the journeys". Performance — measured-only perf audit; no finding without a number. Triggers "perf audit", "performance audit", "why is it slow", "bundle audit", "build is slow". Threat-model — abuse paths. Triggers "threat model", "STRIDE", "attack surface". Motion — animation audit. Triggers "motion audit", "audit the animations". SEO — discoverability + AEO. Triggers "seo audit", "aeo", "answer engine", "llms.txt", "rank better". Debt — `SHORTCUT:` ledger. Triggers "debt ledger", "shortcut ledger". Owns bare "audit the codebase"; single-page CWV fix loops go to /lighthouse.

Eksperimental · TinjauPerlu ditinjauDihasilkan 12 Okt 2026Audit metadata heuristik

Audit

Kepercayaan

Kualitas

Keamanan

Maintain

Pasang

Trust Score OpenAgentSkill

Tinjauan manual

Trust Score OpenAgentSkill

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

Adopsi GitHub

Peringatan

42 star GitHub

Aktivitas star/fork

Peringatan

42 star dan 3 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

2 bulan sejak push

Kejelasan lisensi

Lulus

MIT

Kelengkapan README/SKILL.md

Lulus

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Peringatan

command execution surface, network or browser surface

Ketersediaan pemasangan

Lulus

npx skills add darkroomengineering/cc-settings --skill audit

Keamanan perintah pemasangan

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

Gagal

shell or command execution, filesystem or document access

Bukti repositori

Lulus

https://github.com/darkroomengineering/cc-settings/tree/main/skills/audit

Status peninjauan

Info

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

6 Lulus · 16 Perlu ditinjau

Jalur pemasangan

Lulus

npx skills add darkroomengineering/cc-settings --skill audit

Repositori

Lulus

https://github.com/darkroomengineering/cc-settings/tree/main/skills/audit

Lisensi

Lulus

MIT

Pemeliharaan

Lulus

2 bulan sejak push

Tinjauan AI

Periksa

The skill references an external script `codex-run.ts` (via `bun "$HOME/.claude/src/scripts/codex-run.ts"`) that is not part of the skill repository. This creates a dependency on the user's environment and could be a portability concern if the script is missing or modified.

Kelengkapan README/SKILL.md

Lulus

Usable description available

Risiko dependensi

Perbaiki

command execution surface, network or browser surface

Keamanan perintah pemasangan

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

Perbaiki

shell or command execution, filesystem or document access

Aktivitas star/fork

Perbaiki

42 star dan 3 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

Periksa

42 star GitHub

Peringatan

Dependency or permission surface needs review
Permission surface may require sandboxing
The skill references an external script `codex-run.ts` (via `bun "$HOME/.claude/src/scripts/codex-run.ts"`) that is not part of the skill repository. This creates a dependency on the user's environment and could be a portability concern if the script is missing or modified.
The `requires: mcp: context7` field in the frontmatter may be interpreted as a hard requirement, but the skill text clarifies it is optional and only used when configured. This could cause confusion for users without the MCP.
Low GitHub adoption signal
Quality score needs review
Permission surface needs review: shell or command execution, filesystem or document access
GitHub adoption: 42 GitHub stars
Stars/forks activity: 42 stars, 3 forks; issue activity unavailable in current metadata
Dependency/runtime risk: command execution surface, network or browser surface
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.

Jalur pemasangan

Tinjau laporan sebelum memasang pada Agent produksi.

Tinjau sumber

Metadata yang dapat dibaca Agent

Paket keputusan mesin

JSON tersemat menyediakan tugas dan Agent yang sesuai, perintah pemasangan, skor kepercayaan, gerbang keamanan, alternatif, serta kondisi jangan gunakan untuk ditinjau Agent.

Kebijakan pemasangan: Tinjau
Agent terbaik: Codex + Claude Code
Alternatif: 3

Buka JSON Agent

Sinyal

Skor audit: 71/100
Quality: 60/100
Trust: 64/100
Install safety: 92/100
Cakupan izin: 36/100
Pemeliharaan: 2 bulan sejak push
Event: 8 event
Star GitHub: 42
Push terakhir: 20 Agu 2026

Keamanan Agent v2

39/100 · Hindari pemasangan otomatis

EksperimentalTinjau

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

The tracked source changed or could not be synchronized. Review the current source before installing.

The tracked source changed or could not be synchronized. Review the current source before installing.
Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
skor keamanan Agent 39/100

Eksekusi shell atau perintah

Tinggi

Metadata skill merujuk terminal, CLI, shell, subprocess, atau alur kerja eksekusi perintah.

Akses jaringan

Sedang

Skill kemungkinan mengambil halaman jarak jauh, API, repositori, atau layanan eksternal.

Akses sistem file

Sedang

Skill dapat membaca atau menulis file proyek, dokumen, artefak yang dihasilkan, atau status workspace lokal.

Akses database

Sedang

Skill dapat memeriksa skema, mengkueri database, atau bekerja dengan penyimpanan persisten.

Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
Dependency or permission surface needs review
The tracked source changed or could not be synchronized. Review the current source before installing.

Kembali ke skill Alternatif Badge audit SVG

Bandingkan opsi sekitar

Skill terkait untuk diaudit berikutnya

Wazuh

Wazuh - The Open Source Security Platform. Unified XDR and SIEM protection for endpoints and cloud workloads.

16K Star · Laporan audit

Maigret

🕵️‍♂️ Collect a dossier on a person by username from 3000+ sites

33K Star · Laporan audit

Nuclei

Nuclei is a fast, customizable vulnerability scanner powered by the global security community and built on a simple YAML-based DSL, enabling collaboration to tackle trending vulnerabilities on the internet. It helps you find vulnerabilities in your applications, APIs, networks, DNS, and cloud configurations.

29K Star · Laporan audit