Skills/Content Moderation/Check an image

Check an image

0.1 credits / check

Submits a publicly reachable image URL to the content classifier and returns a verdict across image-capable harm categories: sexual content, violence, and self-harm. Each category includes a calibrated confidence score alongside a boolean flag.

Use when

You want to screen a picture for explicit, violent, or self-harm content before showing or storing it.

Not for

Reading text out of the image, detecting AI-generated or manipulated images, or general image labeling.

Cost

0.1 credits / check

What it accepts

Set these inside the intent when you run it.

image_urlrequired

A publicly reachable URL of the image to check. Must be under 20 MB and not behind a login.

What you get back

An overall flagged verdict, a per-category flag map, and confidence scores for the image-applicable harm categories.

Run it

Run this sub-skill directly: pin it with operation and pass its inputs in the intent. (Omit operation and the Content Moderation skill will route from your intent instead.)

curl -X POST "https://skill.askfaro.com/skills/content-moderation/run" \
  -H "Authorization: Bearer $FARO_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"intent":{"operation":"moderate_image","image_url":"https://example.com/user-upload/photo.jpg"}}'

Example requests

›Is this profile photo appropriate for a family-friendly platform?
›Check this uploaded image for explicit or violent content before storing it
›Does this user-submitted picture contain self-harm imagery?

← Back to Content Moderation