More screenshots
Works with the AI Agents you already use
🚦 Pre-Launch Safety Check
It performs a local, read-only scan of your codebase to identify critical security oversights before they reach production.
$13
🚦 Pre-Launch Safety Check
Example session with this skill installed
I'm about to deploy my Supabase and React app to Vercel. Can you check my code to make sure I didn't leave any doors open or leak any keys?
- Read your context and instructions
- Compiled the pre-launch safety check
⚠️ Pre-Launch Safety Report
[Critical] PLS001 - Exposed API Key
- File:
src/api.js:12 - Evidence:
const STRIPE_KEY = "sk_live_51M..." - Impact: Anyone can use your Stripe account.
- Fix: Move this to an environment variable in Vercel.
[High] PLS004 - Public DB Access
- File:
supabase/migrations/schema.sql - Evidence:
FOR SELECT USING (true); - Impact: Your entire user table is readable by the public.
- Fix: Enable RLS and add a
auth.uid()check.
Manual Checklist:
- Verify Vercel CORS settings limit access to your domain.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The Pre-Launch Safety Check is a specialized audit tool designed to catch the "silent killers" of a new product launch: leaked API keys, unprotected databases, and accidental debug modes. It performs a local, read-only scan of your codebase to identify critical security oversights before they reach production.
Why use this skill
While generic AI prompts might miss subtle configuration errors, this skill uses a structured scanner to cross-reference your code against a database of known security anti-patterns. It translates complex vulnerabilities into "founder-friendly" English, explaining exactly what the risk is and providing the specific remediation steps needed to fix it without breaking your app.
Supported checks
- Hardcoded secrets and API keys (Stripe, AWS, OpenAI, etc.).
- Committed environment variables (.env files).
- Publicly accessible database routes and missing auth guards.
- Permissive Row Level Security (RLS) and CORS configurations.
- Production deployments with debug mode enabled.
- Exposed storage buckets and default admin credentials.
The output provides a prioritized list of findings, severity levels, and a manual checklist for items that require a human eye, such as business logic flaws.
A plain-English pre-launch check for the most common, highest-impact mistakes. It is not a full security audit or a penetration test, and it is heuristic, so it flags likely problems and explains them rather than proving them. Have a professional review anything sensitive before you ship.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Permissions
File Scopes
Read-only. The patterns it checks load from an editable references/safety-rules.json, and every rule has a plain-language write-up in references/explanations.md. It reads no environment variables and writes nothing.