OWASP AI and Agent Security Cheat Sheets

1. AI Agent Security

   Tool permissions, sandboxing and human approval for agents.

2. MCP Security

   Model Context Protocol server trust, tool poisoning and auth.

3. LLM Prompt Injection Prevention

   Input and output controls for prompt injection.

4. RAG Security

   Access control and poisoning risks in retrieval pipelines.

5. Secure AI Model Ops

   Securing model deployment and operations.

6. Secure Coding with AI

   Reviewing and securing AI-generated code.

Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.