Check text

0.1 credits / check

Submits a piece of text to the content classifier and returns a verdict covering all harm categories: sexual content, harassment, hate speech, illicit activity, self-harm, and violence, each with a calibrated 0-to-1 confidence score.

Use when

You want to screen a message, comment, caption, or generated text before acting on it.

Not for

Checking an image, or enforcing a block on the caller's behalf.

Cost

0.1 credits / check

What it accepts

Set these inside the intent when you run it.

textrequired

The exact text to classify. Do not add framing or context around it.

What you get back

An overall flagged verdict, a per-category boolean map, and a calibrated 0-to-1 score for each harm category.

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_text","text":"You should be ashamed of yourself, nobody wants you here."}}'

Example requests

›Is this user comment safe to publish?
›Check this AI-generated caption for inappropriate content
›Does this message contain hate speech or harassment?

← Back to Content Moderation