# OWASP LLM 취약점 Top 10 리스트 v0.1

> Clean Markdown view of GeekNews topic #9400. Use the original source for factual precision when an external source URL is present.

## Metadata

- GeekNews HTML: [https://news.hada.io/topic?id=9400](https://news.hada.io/topic?id=9400)
- GeekNews Markdown: [https://news.hada.io/topic/9400.md](https://news.hada.io/topic/9400.md)
- Type: news
- Author: [xguru](https://news.hada.io/@xguru)
- Published: 2023-06-15T11:06:02+09:00
- Updated: 2023-06-15T11:06:02+09:00
- Original source: [owasp.org](https://owasp.org/www-project-top-10-for-large-language-model-applications/descriptions/)
- Points: 8
- Comments: 0

## Topic Body

LLM의 취약점에 대한 설명, 방지법 등을 시나리오별로 설명   
- LLM01:2023 - Prompt Injections  
- LLM02:2023 - Data Leakage  
- LLM03:2023 - Inadequate Sandboxing  
- LLM04:2023 - Unauthorized Code Execution  
- LLM05:2023 - SSRF Vulnerabilities  
- LLM06:2023 - Overreliance on LLM-generated Content  
- LLM07:2023 - Inadequate AI Alignment  
- LLM08:2023 - Insufficient Access Controls  
- LLM09:2023 - Improper Error Handling  
- LLM10:2023 - Training Data Poisoning

## Comments



_No public comments on this page._