Stop SQL injection at the source — this skill gives AI agents the patterns to use $queryRaw and parameterized queries correctly, making injection a design-time impossibility, not a runtime detection problem.

TL;DR

SQL injection remains the #1 web vulnerability because AI agents (like humans) still write string-concatenated queries. This skill enforces parameterized query patterns — $queryRaw in Prisma, prepared statements in raw SQL — making injection structurally impossible, not just detectable.

**Bottom line:** Inject this skill into your agent's defaults and watch SQL injection vulnerabilities drop to zero. No runtime scanners needed when the pattern itself is safe.

10-Second Pitch

**Pattern enforcement** — Teaches $queryRaw tagged templates, not raw string concat
**Prisma-native** — Works with Prisma ORM's safe query builder
**Auto-fix suggestions** — When an agent writes a dangerous query, it gets corrected
**Audit output** — Shows which queries were verified safe vs. flagged
**Framework-agnostic core** — Safe patterns apply to any SQL database

Setup Directions

Step 1 — Configure Prisma Safe Query Rules

// prisma.safe.js — Add to your Prisma client config

import { PrismaClient } from '@prisma/client';

const prisma = new PrismaClient({

log: ['query', 'error'],

});

// Extend client with safe query helpers

prisma.$safeQuery = (template, ...params) => {

// Enforce parameterized queries only

if (template.includes('\${')) {

throw new Error('Unsafe: Use $queryRaw with tagged template only');

}

return prisma.$queryRaw(template, ...params);

};

Step 2 — Configure the Skill

{

"enforce_parameterized": true,

"allowed_engines": ["prisma", "postgres", "mysql"],

"denylist_patterns": [

"string concatenation with +",

"template literals with user input in \${",

"f-string style injection"

]

}

Pros / Cons

Pros	Cons
Makes injection structurally impossible	Developer education still needed for edge cases

Zero runtime overhead vs. runtime WAF approaches	Some legitimate dynamic queries need extra care

Works with existing codebases	Requires ongoing monitoring for new query patterns

Verdict & Sign-Off

SQL injection is a solved problem — the solution is parameterized queries. The issue is enforcement. This skill makes safe queries the default path for your AI agents, not the exception after a security review.

#security #sql-injection #database #prisma #backend

AI-native — agents get it right by default	Framework-specific patterns may not transfer