Real AI agent use cases, with sources and setup prompts

Scan launched vibe-coded apps for leaked keys and missing security headers

ShipSniffer collected 155 vibe-coded apps launched on Show HN and ran a free passive scan on the 99 still live, checking HTML and JavaScript bundles for secret keys, security headers and Supabase settings.

Free tier10 minutesBeginnerSource linked

Source

jakecyr on Hacker News · 2026-10-17 · Project link

Written in our own words. Credit to the original author. Link checked 2026-10-18.

What they did

ShipSniffer collected 155 vibe-coded apps launched on Show HN and ran a free passive scan on the 99 still live, checking HTML and JavaScript bundles for secret keys, security headers and Supabase settings.

Result (as claimed)

91% had no Content-Security-Policy, 88% could be framed by any site, 37% exposed a Supabase anon key, and only 1 app leaked a secret key (an OpenAI key).

Tools they used

Cost: Lovable: free plan, paid from $25/mo; Replit: free plan, paid from $18/mo; Cursor: free plan, paid from $8/mo. Checked 2026-10-14.

Set it up

  1. Gather your sources

    Collect the papers, notes, links or files you want to work from in one place.

  2. Load them into the tool

    Open Lovable, Replit, Cursor and add your sources. Keep the original files so you can check claims later.

  3. Ask focused questions

    Ask for summaries, comparisons or connections with citations to the source passages.

  4. Verify and save

    Spot check claims against the sources, then save the output as notes you can reuse.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Scan launched vibe-coded apps for leaked keys and missing security headers
What the original author did: ShipSniffer collected 155 vibe-coded apps launched on Show HN and ran a free passive scan on the 99 still live, checking HTML and JavaScript bundles for secret keys, security headers and Supabase settings.
Reported result (as claimed by the author): 91% had no Content-Security-Policy, 88% could be framed by any site, 37% exposed a Supabase anon key, and only 1 app leaked a secret key (an OpenAI key).
Source: https://news.ycombinator.com/item?id=50133249
Tools they used: Lovable, Replit, Cursor
Category: Research & learning

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Guides for this use case

How to vibe code an app with Claude Code · How to secure vibe-coded apps and agents · How to use Cursor agents and automations

Related use cases