Source · docs
OWASP Top 10 for LLM Applications
Summary
A community-maintained list of the most critical security risks for applications built on large language models, with descriptions, examples, and mitigations.
Key points
- Prompt injection is ranked as the top risk.
- Other entries include sensitive information disclosure, supply chain risks, data and model poisoning, improper output handling, excessive agency, and unbounded consumption.
- Each risk comes with prevention guidance.
Why it matters
The standard checklist for threat-modelling an LLM application or agent.