More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Launch Audit: Is Your AI-Built App Safe?

    1

    Scans an AI-built app for leaked keys, open databases and unguarded routes, then gives a plain-English go/no-go before launch.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    A pre-launch safety gate for apps built with AI builders (Lovable, Bolt, Replit, v0, Cursor, Claude, and others), ending in a plain-English GO / GO-WITH-FIXES / NO-GO verdict. It scans the code for leaked secrets, Supabase service_role keys, committed .env files, tables without Row Level Security, open Firebase rules, API routes with no login check, unsigned webhooks, wildcard CORS and SQL injection. Use when the user is about to launch, share or demo an AI-built app, asks "is my app safe", "can I launch", or "check my Lovable/Bolt/Supabase app for security issues", or wants a security check before real users. Works in Claude Code, Codex, Gemini CLI, Cursor and Copilot. Live-tested on Claude Code, Codex and Gemini CLI (eval grade A). Part of Vibe App Launch Audit by Abiodun Anifowose.

    Requires Python 3 for full scan capabilities. Live probes are skipped if network access is restricted. Does not audit cloud billing or financial configurations.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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 25 days ago

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables
    Browser
    Listed25 days ago

    What's inside

    Frequently Asked Questions

    It is specifically designed for apps generated by AI tools like Bolt, Lovable, Cursor, and v0, which often prioritize speed over security configurations like Supabase RLS or Firebase rules.

    The skill includes automated code scanning, live environment probing, a structured audit report with a GO/NO-GO verdict, and specific fix-prompts to resolve any vulnerabilities found.

    No, this skill is designed for non-security experts; it delivers a plain-English report and actionable prompts you can feed back into your AI builder to fix the issues.

    Yes, while optimized for Supabase and Firebase, the skill effectively scans any web application for leaked .env files, exposed API keys, and missing HTTPS or security headers.

    You must confirm ownership of the live URL before network probes begin, and you can choose 'Code-only mode' if you prefer not to run live environment checks.

    The skill provides copy-paste prompts tailored to your specific findings, allowing you to ask your AI builder (like Claude or Cursor) to implement the security fixes automatically.

    New in Security