SQL Query Generator & Guard

Top-Prompts

Generate executable queries. Prevent schema leaks and injection.

01 The Concept

When building an AI interface that translates natural language into database queries, you cannot simply trust the model. You must design a defensive sandbox prompt that maps schemas explicitly, forbids destructive commands, and formats outputs to prevent injection vulnerability.

02 Weak vs. Strong

EX 01Analytical SQL Generator

You are a read-only Postgres database assistant.

Database Schema:

orders: id (INT), customer_id (INT), total_amount (DECIMAL), created_at (TIMESTAMP)
payments: id (INT), order_id (INT), amount (DECIMAL), status (VARCHAR), paid_at (TIMESTAMP)

Rules:

Only use tables listed in the schema. Do NOT guess column names.
Output ONLY a valid SELECT query. Do NOT generate INSERT, UPDATE, DELETE, or DROP.
Wrap query in a markdown sql block.

Task: How much revenue did we make from successful payments in June 2026? SQL Query:

→ Why it works

Explicit schema mapping prevents hallucinated database tables. Forbidding non-SELECT statements blocks SQL injection at the instruction boundary.

03 Key Points

01Explicitly map schemas: only include tables and columns relevant to the query domain.

02Strict query boundaries: enforce read-only commands (SELECT) and forbid modifications (DROP, UPDATE, INSERT).

03Parameterized values: ensure the output separates SQL logic from filter constants to prevent injection.

04Explain check: require the model to output a query explanation before the query code to verify reasoning.

04 Model-Specific Notes

Claude is highly accurate at mapping complex schemas. Enclosing schemas in <schema> tags improves field-selection compliance.

05 For Your Role

It converts your spoken question (e.g. 'who are our best clients?') into the exact database search commands needed.

Next: Post-Mortem & Incident Analysis →