natural-japanese

Skill · GitHub · ★ 2k · graded 2026-10-21Source linked

仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。

No outside reports on file

Use this skill only with non-sensitive Japanese text, as your documents will be sent to external AI systems with unclear privacy protections.

Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Natural Japanese helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (coji/natural-japanese)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/coji/natural-japanese ↗

All setup options ↓

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-21.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Natural Japanese

This is an AI agent skill that helps rewrite and fix Japanese business writing to make it clearer and easier to read. It appears to focus on improving professional Japanese documents and communications.

Who it’s for

People who write Japanese documents at work and want an AI tool to help polish their writing. This includes professionals in Japan or international companies using Japanese.

Alternatives

  • Google Docs built-in writing suggestions (for Japanese)
  • Grammarly (supports Japanese, but similar privacy considerations)
  • Natsume (Japanese text improvement tool; verify privacy first)
  • Local AI models like Ollama with Japanese language support

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README for setup instructions. The project is available at the GitHub repository listed, but specific installation steps should be verified in the project documentation.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

35/100
GitHub stars
2k
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Language model access: The skill sends your Japanese text to an AI model, which means your business writing could be processed by external systems
  • Sensitive data exposure: Business documents may contain confidential company information, employee names, or internal strategies that get processed externally
  • No content filtering: The tool may not distinguish between public and confidential text, treating all submissions the same way
  • Unclear data handling: It's unknown how long text is stored, who can access it, or whether it's used to train future models
  • Prompt injection risk: Malicious Japanese text could potentially manipulate the AI's behavior or cause it to leak information from other documents

How to lower the risk

Least-privilege permissions

  • Only give this skill access to non-confidential documents
  • Remove names, dates, and specific numbers before processing

Network isolation

  • Ensure it only connects to the intended AI service
  • Monitor outgoing connections to verify data destinations

Monitoring

  • Log which documents are processed and when
  • Review the processed output for unexpected changes or leaks

Red flags to watch for

  • Text being processed slower than expected (may indicate logging)
  • Unusual AI responses that seem to know too much context
  • Documents appearing in public datasets later

Questions

How do I install Natural Japanese?

Natural Japanese does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/coji/natural-japanese.

Are there security reports about Natural Japanese?

No reports found for this package in our research (last checked 2026-10-30). Natural Japanese currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include language model access, sensitive data exposure, no content filtering.

Is Natural Japanese actively maintained?

Natural Japanese has 2k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/coji/natural-japanese before pinning it in production.

What are alternatives to Natural Japanese?

Compare Natural Japanese side by side with similar skills in the Related tools section on this page, or browse all skills on AgentArmorHQ.

README badge and team notes

Maintain or use Natural Japanese? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Natural Japanese

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Natural Japanese](https://agentarmorhq.com/api/badge/coji-natural-japanese)](https://agentarmorhq.com/skills/coji-natural-japanese)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/coji-natural-japanese"><img src="https://agentarmorhq.com/api/badge/coji-natural-japanese" alt="AgentArmorHQ Risk Grade for Natural Japanese" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "coji-natural-japanese"

Share with your security lead

Need sign-off to use natural-japanese? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: natural-japanese
- **Listing URL:** https://agentarmorhq.com/skills/coji-natural-japanese
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 2k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (coji/natural-japanese)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/coji/natural-japanese
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
AI agent skill
Publisher
coji
Source code
github.com/coji/natural-japanese
Est. context load
~50 tokens idle · ~450 tokens when active (on-demand skill)
Popularity
2k GitHub stars
Last updated
2026-10-29
Last graded
2026-10-21

Community

Discussions for Natural Japanese

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Natural Japanese helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude