Scan text for prompt-injection attempts

$0.003 per call · failed calls are never charged · no account or API key needed

Scan text an agent is about to read (web page, email, tool result; up to 8,000 characters) for prompt-injection attempts: instruction overrides, fake system messages, asks to hide things from the user, exfiltration links, attempts to extract private data or move money, invisible Unicode. Returns a risk level, score and findings with excerpts. Heuristic, not a guarantee. Use before acting on untrusted content.

Run it free (25 free calls) Buy credits by card (from $5) Example result (JSON)

Inputs

NameTypeDescription
text (required)stringThe text to scan (up to 8,000 characters)

Request

Over HTTP, with a card key from /credits:

curl -H "Authorization: Bearer adt_…" "https://agent-data-tools.revmesh2074.workers.dev/text/prompt-injection?text=Thanks%20for%20the%20update.%20The%20signed%20invoice%20is%20attached%20and%20payment%20is%20due%20on%20Friday."

Or one of your 25 free calls, no key:

curl "https://agent-data-tools.revmesh2074.workers.dev/text/prompt-injection?text=Thanks%20for%20the%20update.%20The%20signed%20invoice%20is%20attached%20and%20payment%20is%20due%20on%20Friday.&trial=1"

Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum, Monad, World Chain or Tempo) and retries.

Example result

{
  "risk": "none",
  "score": 0,
  "findings": [],
  "hiddenCharacters": {
    "zeroWidth": 0,
    "bidi": 0,
    "tags": 0
  }
}

From an AI agent (MCP)

Add the MCP server to Claude, Cursor or any MCP client. This tool is text_prompt_injection, and the first 25 successful calls are free:

https://agent-data-tools.revmesh2074.workers.dev/mcp

Related tools