A community-maintained list of the most important security risks in applications built on language models, such as prompt injection and insecure handling of model output, with mitigations for each.

This is an external publication hosted at owasp.org. AI Governance LK did not write it; the summary and notes on this page are our own.

Why it matters

This is the most practical starting point for teams shipping LLM features. Check the project site for the current edition, as the list is revised as the threat landscape changes.

What you will learn

  • Recognise the most common LLM application vulnerabilities
  • Map each risk to practical controls

Before you start

Suggested background. This is editorial guidance, not a requirement.

  • Basic web application security concepts (helpful)

How to cite

OWASP Foundation. OWASP Top 10 for Large Language Model Applications.