Aller au contenu
TakoAPI
Retour aux skills

didit-passive-liveness

par rosasalberto

Image & Video Generation
—Pas encore noté
Ta note

Résumé

Integrate Didit Passive Liveness standalone API to verify a user is physically present.

Description

Ce que fait ce skill

Calls the Didit Passive Liveness API to verify that a captured image shows a physically present person. Analyzes a single JPEG, PNG, WebP, or TIFF image and returns a liveness score, face quality rating, and luminance value. Detects spoofing attempts including printed photos, screen captures, masks, and deepfakes.

Single-image passive analysis needs no user interaction, cutting friction while maintaining 99.9% liveness detection accuracy.

Quand l'utiliser

  • Blocking bot signups by checking selfie liveness at registration
  • Gating high-risk transactions with a real-person check
  • Flagging deepfake or printed-photo fraud attempts
  • Confirming physical presence before KYC identity verification
  • Detecting duplicate faces across sessions to prevent account sharing

Exemple de workflow

ENTRÉE

User asks: check whether selfie.jpg is a real person

AGENT
  1. 1

    Reads selfie.jpg from disk

  2. 2

    POSTs the image to the Didit passive liveness endpoint with the DIDIT_API_KEY header and an 80-point decline threshold

  3. 3

    Parses the response liveness.status field

  4. 4

    If Declined, extracts the warnings array to identify the failure reason

  5. 5

    Returns the status, liveness score, face quality, and any warning tags

SORTIE

Liveness status 'Approved' with score 95, face_quality 85.0, and no warnings, or 'Declined' with a LIVENESS_FACE_ATTACK warning if spoofing is detected

Prérequis

  • DIDIT_API_KEY environment variable
  • Didit Business Console account at business.didit.me

Installation

clawhub install rosasalberto/didit-passive-liveness

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens