OWASP LLM Top 10

A ranked list of the most critical security risks for LLM applications, published by OWASP. The 2025 edition covers 10 vulnerability classes specific to LLM-powered systems.

Risks Covered So Far

ID	Name	Description
LLM01:2025	Prompt Injection	Manipulating the input prompt to force unintended LLM behavior
LLM02:2025	Sensitive Information Disclosure	Leakage of sensitive data resulting from improper prompt engineering or prompt manipulation

Full List

⚠️ Placeholder: only LLM01 and LLM02 have been ingested so far. Ingest the full OWASP LLM Top 10 document to complete this page.

Source: https://genaisecurityproject.com/resource/owasp-top-10-for-llm-applications-2025/

See Also

• prompt-injection — LLM01 and LLM02 in detail
• google-saif — complementary framework from Google
• prompt-engineering-llm-security — prompt engineering & LLM security overview