スキル address-normalize

📦

address-normalize

Name: address-normalize
Author: tahodev

コンテンツリビジョン r1 低リスク 🌐 ネットワークアクセス📁 ファイルシステムへのアクセス⚙️ 外部コマンド

Normalize Japanese Addresses with Public ABR Data

Japanese addresses contain inconsistent numerals and omitted administrative names. This skill uses public ABR masters to identify address components and codes while preserving the remaining text.

対応: Claude Codex Code(CC)

📊 74 十分

Maintain this Skill? Claim it 📊 74 十分

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト

Review the Skillstore skill "address-normalize" from https://skillstore.io/skills/tahodev-address-normalize.md and its manifest at https://skillstore.io/api/skills/tahodev-address-normalize/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/tahodev-address-normalize.md 署名済み manifest GET /api/skills/tahodev-address-normalize/manifest 署名済み lockfile GET /api/skills/tahodev-address-normalize/lockfile

テストする

「address-normalize」を使用しています。 Normalize 東京都千代田区内幸町1丁目1-1.

期待される結果:

Prefecture: Tokyo. Municipality: Chiyoda.
Town: Uchisaiwaicho, chome 1. Municipality code: 131016. Town identifier: 0001001.
Remaining text: 1-1. The administrative and town components matched; the street number was not validated.

「address-normalize」を使用しています。 Normalize 新宿区歌舞伎町一丁目4-1.

期待される結果:

Prefecture: Tokyo, inferred from Shinjuku municipality.
Town: Kabukicho, chome 1. The kanji numeral matched the town master.
Remaining text: 4-1. Street-level validation is outside this result.

「address-normalize」を使用しています。 Normalize 東京都千代田区内幸町 without a chome.

期待される結果:

Prefecture: Tokyo. Municipality: Chiyoda.
No town match was selected because the candidate records require a chome.
Remaining text: 内幸町. Review the missing chome before accepting the address.

セキュリティ監査

低リスク

v1 • 2026/10/13 バージョン別レポートを開く

Most static alerts are false positives from Markdown, public data URLs, and scoped cache access. Three findings identify one unbounded download and ZIP decompression risk; a semantic finding identifies abolished-record acceptance. No evidence found of prompt injection, credential access, address exfiltration, or malicious intent.

スキャンされたファイル

320

解析済み行数

レビュー項目

誤検知を無視

確認済みのセキュリティ上の懸念 (1)

低

lookup.py:31-32 lookup.py:65-88 SKILL.md:40

Abolished records remain eligible for current-address matches

The documentation requires excluding records with ablt_date, but the helper loads and matches every row. Retired administrative or town records can receive successful matches.

The loader and matching code never check ablt_date, although the documentation explicitly requires it. This establishes a data-integrity defect, not malicious intent.

機能レビュー項目 (3)

これらは、このスキルに期待される可能性のある実際のローカル機能であるため、レビューが必要ですが、確認済みの悪意ある動作としてはカウントされません。

中

lookup.py:28

Fetch API call

z = zipfile.ZipFile(io.BytesIO(fetch(url)))

This loads the entire downloaded archive into memory without a byte cap. An oversized upstream response could exhaust memory despite the request timeout.

中

lookup.py:20

Python HTTP libraries

with urllib.request.urlopen(req, timeout=timeout) as r:

The response is immediately consumed through unrestricted r.read() on line 21. A timeout does not bound memory consumption from an oversized response.

中

lookup.py:28

Python archive libraries

z = zipfile.ZipFile(io.BytesIO(fetch(url)))

The archive member is decompressed through unrestricted z.read(inner) on line 30. A highly compressed oversized member could exhaust memory or disk.

リスク要因

🌐 ネットワークアクセス (11)

lookup.py:18 lookup.py:28 lookup.py:12 lookup.py:19 lookup.py:20 lookup.py:14 SKILL.md:20 SKILL.md:21 SKILL.md:22 SKILL.md:25 SKILL.md:26

📁 ファイルシステムへのアクセス (13)

lookup.py:9 lookup.py:15 lookup.py:9 lookup.py:15 lookup.py:30 lookup.py:24 lookup.py:27 lookup.py:28 SKILL.md:23 SKILL.md:24 SKILL.md:66 SKILL.md:62 SKILL.md:62

⚙️ 外部コマンド (28)

監査者: codex

このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く

レポートリンクをコピー

https://skillstore.io/skills/tahodev-address-normalize/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/tahodev-address-normalize/security.svg)](https://skillstore.io/skills/tahodev-address-normalize?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/tahodev-address-normalize?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tahodev-address-normalize/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/tahodev-address-normalize.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学術引用 (APA · BibTeX · CFF)

APA形式の引用

tahodev. (2026). address-normalize security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/tahodev-address-normalize/audits/1

BibTeX形式の引用

@techreport{tahodev-tahodev-address-normalize-2026,
  author = {tahodev},
  title = {address-normalize security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/tahodev-address-normalize/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "address-normalize security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "tahodev"
date-released: "2026-10-13"
url: "https://skillstore.io/skills/tahodev-address-normalize/audits/1"
identifiers:
  - type: other
    value: "skillstore:tahodev-address-normalize:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore スコア

このスコアの理由証拠の信頼度: 中

アーキテクチャ

保守性

コンテンツ

コミュニティ

仕様準拠

作成できるもの

Prepare customer address records

Separate administrative components and identifiers before reviewing unmatched or ambiguous customer addresses.

Explore municipal town masters

List towns for a selected prefecture and compare keyword results with the published ABR records.

Prototype an address import workflow

Use the Python helper to extract structured address fields before adding current-record filtering and application-specific validation.

これらのプロンプトを試す

Parse one address

Normalize 東京都千代田区内幸町1丁目1-1 with this skill. Present the prefecture, municipality, town, identifiers, and remaining text in plain language.

Compare numeral variants

Compare 新宿区歌舞伎町一丁目4-1 and 新宿区歌舞伎町１丁目4-1. Show whether the town identifiers match and retain each remaining address portion.

Find town candidates

List Tokyo town records with prefecture code 13 and keyword 歌舞伎. Present municipality codes, town identifiers, and labels without claiming delivery validation.

Review an address import

Review these addresses: [address list]. Check ambiguous municipalities, abolished records, missing chome, and cache age. Separate reliable matches from unresolved entries.

ベストプラクティス

Refresh masters when freshness matters, then independently exclude abolished records and verify ambiguous municipality matches.
Review unmatched results and remaining text before importing records or using them for operational decisions.
Attribute the Digital Agency's Address Base Registry and follow the documented data licensing terms.

回避

Treating a successful town match as proof that a street number exists or that an address is deliverable.
Assuming --pref constrains address parsing or that omitted prefectures always produce an unambiguous municipality.
Using cached or abolished records as current authoritative addresses without reviewing master dates and status fields.

よくある質問

Which assistants can use this skill?

The report lists Claude, Codex, and Claude Code. Running the included helper requires an environment with Python 3.

Does it require an API key or account?

No. The helper downloads public ABR master files without credentials.

Are input addresses sent to a remote service?

The helper matches addresses locally. Its requests download public masters and do not include the input address.

Can it work offline?

Yes, when all required master CSV files are already cached. Initial downloads and requested refreshes require network access.

Does it validate street numbers or return coordinates?

No. Street numbers and building details remain outside its normalization scope. Geocoding requires a separate tool.

Does it guarantee a current, unambiguous address match?

No. The helper does not exclude abolished records or reject ambiguous municipalities. The --pref option selects town-list data but does not constrain address parsing.