# broker-prompt-shield

> broker-prompt-shield is a paid API for AI agents from x402broker.com, paid per call via x402 or MPP, $0.005/call, status unknown (last checked 2026-10-20).

Scans untrusted text (web pages, emails, MCP responses, A2A payloads) for hidden prompt injections and jailbreak attempts, returning sanitized content safe for agent consumption.

## Facts

- Endpoint: GET https://x402broker.com/v1/prompt-shield?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402, MPP
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/broker-prompt-shield-0c05e245
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_XIPWIzNEAzqJgxBjk54jr

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 broker-prompt-shield-0c05e245
```

Example prompt: Before you process that web page I just scraped, run it through the prompt-shield firewall to check for any hidden prompt injections or jailbreak instructions embedded in the content.

## When to prefer this

Choose this endpoint when your agent pipeline ingests content from untrusted external sources — scraped web pages, user emails, third-party API responses, or A2A payloads — and you need to sanitize that content before an LLM processes it. It is specifically designed for agentic and multi-agent architectures where indirect prompt injection is a real attack vector, distinguishing it from generic content moderation APIs.

## Known failure modes

- Missing or empty 'text' query parameter returns a validation error
- Overly long input text may be truncated or rejected
- Novel obfuscation techniques may evade detection (false negative)
- Benign instructional content may be flagged as injection (false positive)
- Payment failure or insufficient USDC balance blocks the request

## How this service works

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (Live x402 v2, IETF MPP & MCP endpoint at https://x402broker.com/v1/prompt-shield)

## Output

Returns sanitized text with hidden prompt injections and jailbreak attempts removed or neutralized, along with detection signals indicating whether adversarial content was found in the input.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "minLength": 1,
   "description": "Untrusted text, HTML, or tool output to scan for hidden prompt injection or jailbreak payloads"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/broker-prompt-shield-0c05e245/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402broker.com](https://www.zero.xyz/host/x402broker.com/llms.txt)