# OWASP Top 10 for Large Language Model Applications ja

This is the unofficial Japanese translation of the [OWASP Top 10 for Large Language Model Applications](https://github.com/OWASP/www-project-top-10-for-large-language-model-applications).

* Document Site - <https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/>
* Document Repository - <https://github.com/coky-t/owasp-top-10-for-large-language-model-applications-ja>

### Originator

* Official Site - <https://genai.owasp.org/>
* Project Site - <https://owasp.org/www-project-top-10-for-large-language-model-applications/>
* Project Repository - <https://github.com/OWASP/www-project-top-10-for-large-language-model-applications>
* Document Site - <https://genai.owasp.org/llm-top-10/>

## OWASP Top 10 大規模言語モデルアプリケーション 日本語版

* [OWASP Top 10 大規模言語モデルアプリケーション](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon/index)
* [リーダー](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon/leaders)

## OWASP Top 10 大規模言語モデルアプリケーション 2.0 (2025) 日本語版

* [LLM01:2025 プロンプトインジェクション (Prompt Injection)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm01_promptinjection)
* [LLM02:2025 機密情報の開示 (Sensitive Information Disclosure)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm02_sensitiveinformationdisclosure)
* [LLM03:2025 サプライチェーン (Supply Chain)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm03_supplychain)
* [LLM04:2025 データおよびモデルポイズニング (Data and Model Poisoning)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm04_datamodelpoisoning)
* [LLM05:2025 不適切な出力処理 (Improper Output Handling)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm05_improperoutputhandling)
* [LLM06:2025 過剰なエージェンシー (Excessive Agency)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm06_excessiveagency)
* [LLM07:2025 システムプロンプトの漏洩 (System Prompt Leakage)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm07_systempromptleakage)
* [LLM08:2025 ベクトルとエンベディングの脆弱性 (Vector and Embedding Weaknesses)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm08_vectorandembeddingweaknesses)
* [LLM09:2025 誤情報 (Misinformation)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm09_misinformation)
* [LLM10:2025 無制限の消費 (Unbounded Consumption)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-20-2025/llm10_unboundedconsumption)

## OWASP Top 10 大規模言語モデルアプリケーション 1.1 日本語版

* [LLM01: プロンプトインジェクション (Prompt Injection)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm01_promptinjection)
* [LLM02: 安全でない出力処理 (Insecure Output Handling)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm02_insecureoutputhandling)
* [LLM03: 訓練データポイズニング (Training Data Poisoning)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm03_trainingdatapoisoning)
* [LLM04: モデルサービス拒否 (Model Denial of Service)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm04_modeldos)
* [LLM05: サプライチェーン脆弱性 (Supply Chain Vulnerabilities)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm05_supplychainvulnerabilities)
* [LLM06: 機密情報の開示 (Sensitive Information Disclosure)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm06_sensitiveinformationdisclosure)
* [LLM07: 安全でないプラグイン設計 (Insecure Plugin Design)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm07_insecureplugindesign)
* [LLM08: 過剰なエージェンシー (Excessive Agency)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm08_excessiveagency)
* [LLM09: 過度の依存 (Overreliance)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm09_overreliance)
* [LLM10: モデル窃取 (Model Theft)](https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/owasp-top-10-moderuapurikshon-11/llm10_modeltheft)

## License

[Creative Commons Attribution-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-sa/4.0/)

## Translator (Japanese)

[Koki Takeyama](https://github.com/coky-t)

* Document Site - <https://coky-t.gitbook.io/owasp-docs-ja/>
* Document Repository - <https://github.com/coky-t/owasp-docs-ja>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://coky-t.gitbook.io/owasp-top-10-for-large-language-model-applications/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.