# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from x402broker.com, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-21).

Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized content.

## Facts

- Endpoint: GET https://x402broker.com/v1/rag-poison-shield?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: x402broker.com
- Website: https://x402broker.com
- Canonical page: https://www.zero.xyz/c/x402broker-com-a2a-indirect-prompt-injection-jailbreak-firewall-1d15aec7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mxL5wTKDTDu5hqgD4BzgP

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 x402broker-com-a2a-indirect-prompt-injection-jailbreak-firewall-1d15aec7
```

Example prompt: Before you use that scraped webpage content in your reasoning, run it through the prompt-injection firewall — I want to make sure there are no hidden instructions or jailbreak payloads embedded in the HTML before you process it.

## When to prefer this

Choose this endpoint when you need to protect an AI agent pipeline from indirect prompt injection attacks originating from untrusted external sources such as scraped web pages, third-party tool responses, emails, or A2A/MCP payloads. Prefer it over manual filtering when the untrusted content is HTML or structured data that may contain steganographic or invisible-text injection techniques. Ideal for RAG pipelines, multi-agent architectures, and any system where an LLM consumes externally sourced content.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Very large payloads may be truncated or rejected
- Highly obfuscated injections using encoding tricks may evade detection
- Service may return 402 Payment Required if micropayment is not provided via x402 protocol
- Ambiguous or borderline injections may produce false positives or false negatives

## 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/rag-poison-shield)

## Output

Returns a JSON object indicating whether a prompt injection or jailbreak payload was detected in the input text, along with a sanitized version of the content safe for downstream LLM consumption.

## 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/x402broker-com-a2a-indirect-prompt-injection-jailbreak-firewall-1d15aec7/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)