> ## Documentation Index
> Fetch the complete documentation index at: https://docs.proofable.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Content safety

> Screen user text or images for unsafe content before you publish, grant access, or let an agent act. Reusable results across surfaces.

**Verifier ID:** `ai-content-moderation`

Screen text or images for safety, then reuse the result before you publish.

## Use cases

* User-generated content
* AI-generated output
* Moderation and publishing workflows

## Flow type

External lookup. Proofable screens the content with a moderation provider and records the outcome.

## Fields

| Field | Required | Notes |
| - | - | - |
| `content` | Yes | Raw text, base64, or an `ipfs://` / CID reference |
| `contentType` | Yes | MIME type. See supported types below |
| `provider` | No | Defaults by content: text → `google-perspective`, images → `google-vision` |

**Supported `contentType` values:** `text/plain`, `text/markdown`, `text/x-markdown`, `application/json`, `application/xml`, `image/jpeg`, `image/png`, `image/gif`, `image/webp`.

## Example

```json theme={"system"}
{
  "content": "Text to screen, or a base64/ipfs:// reference",
  "contentType": "text/plain"
}
```

Full schema: [`ai-content-moderation.json`](https://github.com/proofable/docs/blob/main/verifiers/schemas/ai-content-moderation.json).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.