# What is the OWASP Top 10 for LLM applications?

It is a list of the most important security risks for applications built on large language models (LLMs), published by the Open Worldwide Application Security Project (OWASP), the community behind the well-known web application Top 10. The 2025 edition names prompt injection, sensitive information disclosure, supply-chain risks, data and model poisoning, improper output handling, excessive agency, system prompt leakage, weaknesses in vector databases and embeddings, misinformation, and unbounded consumption of resources. For a company that only uses AI tools, three items matter most: sensitive information disclosure, which is the shadow-AI problem; excessive agency, meaning AI agents with more permissions than they need; and prompt injection, which turns any document or web page an agent reads into a possible attack. For a company that builds AI features into its own product, the whole list is a sensible checklist for design reviews and tests, and a common vocabulary for customers' security questionnaires. It is guidance, not a standard or a certification.

FAQ: [AI use and AI security](https://netsenx.com/en/faq/ai) · https://netsenx.com/en/faq/what-is-the-owasp-top-10-for-llm-applications

## Read next

- https://netsenx.com/en/shadow-ai-detection
- https://netsenx.com/en/ai-transparency

## Related questions

- [How do we protect confidential data when using LLMs in production?](https://netsenx.com/en/faq/how-to-protect-confidential-data-when-using-llms-in-production)
- [What is the Model Context Protocol (MCP)?](https://netsenx.com/en/faq/what-is-the-model-context-protocol)
- [What is a shadow MCP server and why is it a risk?](https://netsenx.com/en/faq/what-is-a-shadow-mcp-server)
- [How do I discover AI agents running in our company?](https://netsenx.com/en/faq/how-to-discover-ai-agents-running-in-our-company)
- [Should AI agents be treated as privileged automated users?](https://netsenx.com/en/faq/should-ai-agents-be-treated-as-privileged-users)