# Agent Toolkit – Web Page to Markdown with Prompt-Injection Scan

> Agent Toolkit – Web Page to Markdown with Prompt-Injection Scan is a paid API for AI agents from agent-data.centorprat.workers.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-30).

Fetches any public URL and returns clean markdown (main content only) with metadata and a prompt-injection safety scan for LLM agents

## Facts

- Endpoint: GET https://agent-data.centorprat.workers.dev/web/read?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-toolkit-web-page-to-markdown-with-prompt-injection-scan-c85555d1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nr0SQ4mNv7wKHKB8zlaes

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-toolkit-web-page-to-markdown-with-prompt-injection-scan-c85555d1
```

Example prompt: Read this article for me — https://example.com/some-article — strip out all the ads and navigation, give me the main content as clean text, and let me know if the page is trying to inject any hidden instructions into you.

## When to prefer this

Choose this endpoint when your agent needs to safely ingest web content for LLM processing — especially when you need both clean markdown extraction AND a prompt-injection safety check in a single call. It is preferable over raw URL fetchers when you want boilerplate stripped automatically and metadata extracted. The built-in injection scan makes it uniquely suited for agentic pipelines where the agent might act on page content, as it detects adversarial instructions hidden in HTML, comments, or invisible Unicode that a naive scraper would miss. Its Cloudflare edge delivery (~0.5s) makes it suitable for real-time agent workflows.

## Known failure modes

- URL is unreachable or returns non-200 status — endpoint reports failure but does not charge
- Invalid or malformed URL — request rejected with validation error
- Page behind authentication or paywall — only publicly accessible content is returned
- Very large pages may be truncated at max_chars limit (default 20000, max 100000)
- Dynamic JavaScript-rendered content may not be fully captured if server-side rendering is absent

## How this service works

Pay-per-call data and tools for AI agents, $0.002-0.01 per call in USDC via x402 (Base, Polygon or Solana), no account or API key; MAX tiers ($0.05-0.25) run deeper jobs. Agent toolkit: web search, search + read top pages, any page as clean markdown with a prompt-injection check, which-x402-API-to-call recommender, seller check. Data: Google Maps places with contacts, YouTube video data and transcripts, job listings (Indeed, LinkedIn, 13 boards), Google Ads Transparency, TikTok comments, Pinterest, Airbnb, Redfin, AliExpress, app stores, live sports, website and SEO checks, Shopify store tech stacks, and onchain token / address risk checks.

## Output

Returns clean markdown of the page's main content (stripped of navigation, ads, cookie banners), plus structured metadata: title, description, author, publish/modify dates, language, headings outline, internal and external links, JSON-LD semantic types, and a prompt-injection safety report covering visible text, hidden HTML, comments, and invisible Unicode characters.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public http(s) URL"
      },
      "max_chars": {
       "type": "string",
       "description": "Max markdown characters, 500-100000 (default 20000)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "Example article",
  "safety": {
   "verdict": "safe",
   "riskScore": 0
  },
  "markdown": "# Heading\n\nBody text...",
  "wordCount": 1935
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-toolkit-web-page-to-markdown-with-prompt-injection-scan-c85555d1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data.centorprat.workers.dev](https://www.zero.xyz/host/agent-data.centorprat.workers.dev/llms.txt)