# OWASP LLM Top 10 (2025) — designpattern.fyi

> The OWASP Top 10 for Large Language Model Applications - critical security risks for AI-powered applications.

- **Section**: OWASP LLM Top 10 (2025)
- **Canonical URL**: https://designpattern.fyi/owasp_llm/

---

## Patterns in this Category


### [LLM01 - Prompt Injection](https://designpattern.fyi/owasp_llm/llm01_prompt_injection/)
- **Summary**: Adversaries manipulate model behavior by embedding malicious instructions in inputs.
- **Subcategory**: top10_2025


### [LLM02 - Sensitive Information Disclosure](https://designpattern.fyi/owasp_llm/llm02_sensitive_info_disclosure/)
- **Summary**: LLM inadvertently reveals confidential data from training data or retrieved context.
- **Subcategory**: top10_2025


### [LLM03 - Supply Chain Vulnerabilities](https://designpattern.fyi/owasp_llm/llm03_supply_chain/)
- **Summary**: Risks from compromised third-party datasets, models, plugins, or libraries.
- **Subcategory**: top10_2025


### [LLM04 - Data and Model Poisoning](https://designpattern.fyi/owasp_llm/llm04_data_model_poisoning/)
- **Summary**: Attackers manipulate training or fine-tuning data to compromise model integrity.
- **Subcategory**: top10_2025


### [LLM05 - Improper Output Handling](https://designpattern.fyi/owasp_llm/llm05_improper_output/)
- **Summary**: Insufficient validation of LLM output leading to XSS, RCE, or other vulnerabilities.
- **Subcategory**: top10_2025


### [LLM06 - Excessive Agency](https://designpattern.fyi/owasp_llm/llm06_excessive_agency/)
- **Summary**: LLM system granted too much autonomy or overly permissive access to tools and APIs.
- **Subcategory**: top10_2025


### [LLM07 - System Prompt Leakage](https://designpattern.fyi/owasp_llm/llm07_system_prompt_leakage/)
- **Summary**: Exposure of hidden system prompt instructions that define model behavior and constraints.
- **Subcategory**: top10_2025


### [LLM08 - Vector and Embedding Weaknesses](https://designpattern.fyi/owasp_llm/llm08_vector_embedding_weaknesses/)
- **Summary**: Security risks from vulnerabilities in vector databases and embedding methods.
- **Subcategory**: top10_2025


### [LLM09 - Misinformation](https://designpattern.fyi/owasp_llm/llm09_misinformation/)
- **Summary**: LLM generates inaccurate, biased, or hallucinated content treated as truth.
- **Subcategory**: top10_2025


### [LLM10 - Unbounded Consumption](https://designpattern.fyi/owasp_llm/llm10_unbounded_consumption/)
- **Summary**: Failure to impose limits on LLM resource consumption leading to DoS or excessive costs.
- **Subcategory**: top10_2025



---

## Machine-Readable Resources
- **JSON Feed**: https://www.designpattern.fyi/api/patterns.json
- **OpenAPI 3.1**: https://www.designpattern.fyi/api/openapi.json
- **llms.txt**: https://www.designpattern.fyi/llms.txt