OWASP Top 10 for LLM Applications
OWASP's ranked list of the most critical security risks in applications built on large language models.
The 2025 edition lists: LLM01 Prompt Injection, LLM02 Sensitive Information Disclosure, LLM03 Supply Chain, LLM04 Data and Model Poisoning, LLM05 Improper Output Handling, LLM06 Excessive Agency, LLM07 System Prompt Leakage, LLM08 Vector and Embedding Weaknesses, LLM09 Misinformation, LLM10 Unbounded Consumption.
Use it as a threat modelling checklist for any LLM feature, not as a compliance target. In interviews the strongest answers connect entries to classic controls: improper output handling is injection into whatever consumes the output (XSS, SQL, shell), excessive agency is least privilege for tools, unbounded consumption is rate limiting and cost caps.