Security and privacy decision

Spy Camera Scanner

A technically competent developer can reproduce basic Wi‑Fi, BLE, magnetometer and camera-filter functionality, but the app's stated value rests on a proprietary on‑device ML model and product polish that are not reproduced easily; build a narrow sweep tool, but keep paying for the full product if you need the vendor's claimed detection accuracy and tuning.

View on the App Store
You pay

$2.5/mo

$30/yr

Read off the official pricing page.

You’d pay instead

$100one-off120 h to build

$0/mo4 h/mo upkeep

On cash alone, building overtakes the subscription at 4 seats.

No open-source build does this yet

Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.

What a replacement has to do

  • Point phone camera for on-device AI lens detection; scan local Wi‑Fi for devices and suspicious MAC/vendor signatures; sweep for Bluetooth trackers while showing signal strength; enable IR filter to reveal IR LEDs; read magnetometer to show EMF spikes.

What it still won’t have

  • The vendor's "proprietary on-device AI" lens recognition
  • Polish and tuning for low false positives across many camera types
  • App Store brand, existing user reviews, and subscription management history
  • Ongoing model improvements claimed by the vendor

What remains hard

  • Proprietary modelsOur proprietary on-device AI analyzes optical reflection and aperture geometry in real-time to identify hidden pinhole cameras, webcams, and concealed camcorders.
  • Execution qualitySpeed & Polish: Faster launch times and essential bug fixes keep your sweeps perfectly smooth.
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 4 seats.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal iOS hidden-camera sweep app in Swift + SwiftUI that runs fully on-device. Stack: Xcode, Swift 5+, AVFoundation for camera preview, CoreML (use a public object-detection model converted to CoreML) for lens detection, Network framework for local Wi‑Fi enumeration, CoreBluetooth for BLE scanning, and CoreMotion/CMDeviceMotion for magnetometer access. Core features in scope: realtime camera preview with on-device ML lens highlights; Wi‑Fi device list with vendor lookup and a flagged/unknown heuristic; BLE scanner with RSSI meter and simple trace UI; IR visualization mode (camera preview with adjustable sensitivity); magnetometer baseline auto-calibration and spike alerts; simple Settings and StoreKit subscription stub (local switchable premium unlock for testing). Out of scope: training a proprietary lens model, backend/cloud analytics, and automated firmware detection. Deliverables: error handling for sensor/permission failures, unit/UI tests for detection flows, and a README with provisioning and TestFlight instructions.
How we checked2 sources · 2/3 runs agreed · evidence score 21

How the score was reached

  • Pay verdict base20
  • 2 cited sources+1
  • Price verified on pricing page+3
  • Hard moats found in the evidence-3
  • Evidence score21

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 2 moats quoted from the page