What it does
The comprehensive open-source guide to AI security maintained by OWASP. Covers threats, controls, and governance across the entire AI lifecycle. The definitive reference for understanding the AI threat landscape.
Security relevance
This is the single most important reference document in AI security. It maps threats across all 10 LLM risks, provides control recommendations, and connects to the broader OWASP ecosystem. If you read one resource, make it this one.
When to use it
Use as your foundational reference when building AI security programmes, writing policies, or assessing risks. Consult it when mapping controls to specific threats. Updated regularly by the OWASP community.
OWASP coverage
Risks addressed — mapped to both OWASP Top 10 standards. 10 in LLM, 10 in Agentic.
The raw record
What Yuntona stores. Single source of truth — fork it on GitHub.
name: OWASP AI Exchange slug: owasp-ai-exchange type: Mixed category: AI Governance & Standards url: https://owaspai.org reviewed: 2026-04 added: 2026-04 updated: 2026-04 risks: llm: [LLM01, LLM02, LLM03, LLM04, LLM05, LLM06, LLM07, LLM08, LLM09, LLM10] asi: [ASI01, ASI02, ASI03, ASI04, ASI05, ASI06, ASI07, ASI08, ASI09, ASI10] complexity: Plug & Play pricing: — audience: All lifecycle: [govern] tags: [OWASP, Reference, Standard]