# Read a web page as clean Markdown with a prompt-injection scan

**Use case:** 

Give an AI agent a web page without the hidden traps. This example reads the Wikipedia article on empanadas and returns the visible main content as clean Markdown, after removing hidden text, invisible characters and suspicious links. The aiSafety report lists every prompt-injection attempt found. Replace the URL with your own pages. Failed pages are not charged.

## Input

```json
{
  "urls": [
    "https://en.wikipedia.org/wiki/Empanada"
  ],
  "maxResults": 3,
  "searchCountry": "",
  "searchLanguage": "en",
  "mainContentOnly": true,
  "keepLinks": true,
  "removeHiddenContent": true,
  "renderJavaScript": "auto",
  "maxPdfPages": 100,
  "wrapAsUntrusted": false,
  "respectRobotsTxt": true,
  "maxConcurrency": 5,
  "proxyConfiguration": {
    "useApifyProxy": false
  }
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "aiSafety.riskLevel": {
    "label": "Injection risk",
    "format": "text"
  },
  "aiSafety.findingsCount": {
    "label": "Findings",
    "format": "number"
  },
  "wordCount": {
    "label": "Words",
    "format": "integer"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The Safe Web Reader for AI: URL to Markdown + Prompt-Injection Scan Actor is ready to run with the inputs already set for "Read a web page as clean Markdown with a prompt-injection scan". [Sign up or log in](https://console.apify.com/create-task-from-example/NgfyfYy5x4tnXnchX) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Read a web page as clean Markdown with a prompt-injection scan" task

The Safe Web Reader for AI: URL to Markdown + Prompt-Injection Scan Actor will start running based on the input automatically. You can also change all the input fields, like URLs, results to read, and more, to match your specific use case.

### 3. Receive the "Read a web page as clean Markdown with a prompt-injection scan" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as URL, title, injection risk, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Read a web page as clean Markdown with a prompt-injection scan" task via API](https://apify.com/bigochelo/safe-web-reader.md).

## About this Actor

This example demonstrates how to use [Safe Web Reader for AI: URL to Markdown + Prompt-Injection Scan](https://apify.com/bigochelo/safe-web-reader.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/bigochelo/safe-web-reader.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/bigochelo/safe-web-reader.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).
