Guides

Securing database access for AI agents — the specific problems QueryShield solves.

How do I block DELETE and DROP from LLM-generated SQL?

Read-only database users help, but they are not enough to protect a database from AI agents. Learn how AST-level SELECT-only validation blocks DELETE, DROP, UPDATE, and stacked statements before they reach your database.

How do I prevent SQL injection from LLM-generated queries?

Text-to-SQL security is more than escaping strings. Learn how AST validation, allow-listing, and per-agent guardrails stop SQL injection and prompt-injection attacks in LLM-generated SQL.

How do I enforce RBAC for AI agents accessing a database?

Database access control for LLM agents means scoping each agent to only the rows and tables it needs. Learn how per-agent row-level security and scoped API keys enforce least-privilege permissions for AI agents.

Enforce this automatically with QueryShield

A secure SQL proxy for AI agents: natural language in, SELECT-only validated SQL out, per-agent row-level security, and an append-only audit log. Your agents never see connection strings.

Get an API key — free tier Read the API docs