📦

aozora

Name: aozora
Author: tahodev

Content revision r1 Low Risk 🌐 Network access📁 Filesystem access⚙️ External commands

Search Aozora Bunko and Extract Literary Text

Finding Japanese literary texts requires navigating catalog records and inconsistent page encodings. This skill searches the official catalog and extracts readable text from linked works.

Supports: Claude Codex Code(CC)

📊 73 Adequate

Maintain this Skill? Claim it 📊 73 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

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

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/tahodev-aozora.md Signed manifest GET /api/skills/tahodev-aozora/manifest Signed lockfile GET /api/skills/tahodev-aozora/lockfile

Test it

Using "aozora". Find 吾輩は猫である and show its catalog metadata.

Expected outcome:

Illustrative fixture result: 吾輩は猫である, work ID 000789.
Author: 夏目漱石. Kana reading: わがはいはねこである.
Orthography: modern characters and modern kana. Catalog copyright flag: none.
First publication: Hototogisu, January 1905.
Card: https://www.aozora.gr.jp/cards/000148/card789.html

Using "aozora". Show the available reading and download links for work 000789.

Expected outcome:

Illustrative fixture result: 吾輩は猫である by 夏目漱石.
XHTML text: https://www.aozora.gr.jp/cards/000148/files/789_14547.html
Ruby text ZIP: https://www.aozora.gr.jp/cards/000148/files/789_ruby_5639.zip
Ebook: https://www.aozora.gr.jp/cards/000148/files/789.ebk

Security Audit

Low Risk

v1 • 10/13/2026 Open versioned report

Most alerts are harmless Markdown, Japanese text, fixture references, or scoped cache maintenance. Confirmed risks involve unchecked fetch destinations, redirects, and unbounded download or ZIP expansion sizes. No evidence found of prompt injection or credential exfiltration, but the advertised public-domain scope is not enforced.

Files scanned

494

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:3 SKILL.md:40 lookup.py:108-127 lookup.py:137-152

Public-domain scope is not enforced

The description presents copyright-expired works, but searches include copyright-flagged entries. Text retrieval lacks a copyright check and omits copyright status, potentially misleading users about reuse.

The documentation acknowledges copyrighted entries, while retrieval performs no rights check. Search reports flags but does not filter them; no actual infringement is established.

Capability review items (7)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

lookup.py:22

Fetch API call

def fetch(url, timeout=60):

The fetch helper accepts arbitrary URLs without scheme or host validation. Catalog-controlled URLs can therefore trigger requests outside the intended Aozora service.

Medium

lookup.py:33

Fetch API call

zf = zipfile.ZipFile(io.BytesIO(fetch(CSV_URL)))

The catalog ZIP download reads the entire response into memory without a byte limit. An oversized upstream response can exhaust process memory.

Medium

lookup.py:116

Fetch API call

links = parse_card_links(fetch(wr[0]["図書カードURL"]).decode("utf-8", errors="replace"))

The card URL from the catalog is fetched even when card_url_to_base rejects it. An untrusted CSV can direct requests to internal services.

Medium

lookup.py:124

Fetch API call

raw = fetch(out["text_url"])

The text URL initially uses the Aozora base, but fetch follows redirects without checking destinations. Redirects can reach unintended hosts or internal services.

Medium

lookup.py:23

Python HTTP libraries

req = urllib.request.Request(url, headers=UA)

Request receives an unchecked URL from fetch, including catalog-provided values. Without validation, this request construction supports unintended network destinations.

Medium

lookup.py:24

Python HTTP libraries

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

urlopen permits unchecked destinations and follows redirects, then r.read loads all response bytes. This enables unintended requests and memory exhaustion.

Medium

lookup.py:33

Python archive libraries

zf = zipfile.ZipFile(io.BytesIO(fetch(CSV_URL)))

The downloaded ZIP is decompressed through zf.read without entry-size or compression-ratio checks. A highly compressed entry can exhaust memory or disk space.

Risk Factors

🌐 Network access (22)

📁 Filesystem access (17)

lookup.py:35 lookup.py:30 lookup.py:15 lookup.py:33 SKILL.md:36 SKILL.md:55 SKILL.md:36 SKILL.md:55 tests/fixtures/card789.html:89 tests/fixtures/card789.html:103 tests/fixtures/card789.html:120 tests/fixtures/card789.html:122 tests/fixtures/card789.html:129 tests/fixtures/card789.html:134 tests/fixtures/card789.html:173 tests/fixtures/card789.html:183 tests/fixtures/card789.html:193

⚙️ External commands (13)

SKILL.md:16 SKILL.md:22 SKILL.md:23 SKILL.md:24 SKILL.md:28-34 SKILL.md:34-36 SKILL.md:36-40 SKILL.md:40-47 SKILL.md:47 SKILL.md:49 SKILL.md:51 SKILL.md:55-56 SKILL.md:56

Audited by: codex

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

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

Markdown badge

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

HTML badge

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

Embed card

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

Academic citations (APA · BibTeX · CFF)

APA citation

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

BibTeX citation

@techreport{tahodev-tahodev-aozora-2026,
  author = {tahodev},
  title = {aozora security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/tahodev-aozora/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: "aozora security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "tahodev"
date-released: "2026-10-13"
url: "https://skillstore.io/skills/tahodev-aozora/audits/1"
identifiers:
  - type: other
    value: "skillstore:tahodev-aozora:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Locate Literary Reading Material

Find works by title or author and inspect readings, orthography, copyright flags, and links before choosing classroom material.

Inspect Catalog Records

Retrieve work identifiers, publication details, and contributor roles from official catalog records and linked cards.

Prepare Text Samples

Extract bounded plain-text samples without ruby readings from selected works after checking rights and source provenance.

Try These Prompts

Find a Title

Search Aozora Bunko for 吾輩は猫である. Show the work ID, author, kana reading, copyright flag, and card URL.

List an Author's Works

Find up to ten works by 夏目漱石. Show titles, work IDs, orthography, and copyright flags, then report the total matching works.

Retrieve a Text Excerpt

Check copyright status for work 000789, resolve its card links, and retrieve the first 500 plain-text characters without ruby readings.

Inspect a Local Catalog

Use my trusted local Aozora CSV without network access. Report row, work, person, and copyright-flagged counts; explain duplicate contributor rows.

Best Practices

Check each work's copyright flag and applicable permissions before reusing or distributing text.
Use trusted catalog data and restrict network destinations when running the helper.
Use exact stored names, preserve six-digit work IDs, and choose character limits for manageable excerpts.

Avoid

Treating every catalog entry as public domain or assuming online access grants unrestricted reuse.
Guessing text URLs from work IDs instead of reading the book-card links.
Using catalog row counts as work counts or treating snapshot statistics as current live totals.

Frequently Asked Questions

Does this skill require an API key or account?

No. It reads the public Aozora catalog and linked pages without authentication. The helper uses Python standard-library modules.

Can I use it with Claude, Codex, and Claude Code?

The skill declares support for all three. Running the helper requires Python 3, filesystem access, and network access for remote retrieval.

Are all returned works public domain?

No. The catalog includes copyright-flagged works, and the helper does not filter them automatically. Check rights before reuse.

Can I search without network access?

Yes. Supply a trusted local catalog CSV for title searches, author searches, or statistics. Card resolution and remote text retrieval still require network access.

Why can a title or author search miss a work?

Searches use stored spelling and exact concatenated author names. Historical characters, spaces, or an outdated catalog can affect matches.

Does this find current book stock or library holdings?

No. It covers Aozora literary records and available texts, not retail inventory, exhaustive bibliography, or library holdings.