# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from shopify-spy.agentdiet.dev, 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 output.

## Facts

- Endpoint: GET https://shopify-spy.agentdiet.dev/v1/mcp-injection-firewall?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: shopify-spy.agentdiet.dev
- Website: https://shopify-spy.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/shopify-spy-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-01a6dee3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CXSk731I6hLdrqRDIev89

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 shopify-spy-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-01a6dee3
```

Example prompt: Before you summarize that webpage, scan its raw HTML for any hidden prompt injections or jailbreak payloads — I don't want malicious instructions sneaking into your context.

## When to prefer this

Choose this endpoint when your AI agent is about to process text, HTML, or structured payloads retrieved from untrusted external sources — especially web scraping results, user-submitted content, third-party API responses, or MCP/A2A tool outputs — and you need to detect and strip adversarial prompt injections before they reach your LLM context. Particularly valuable in agentic pipelines where tool outputs could contain hidden instructions targeting the agent.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long payloads may be truncated or rejected
- Obfuscated injections using novel encoding may evade detection
- Service may return a 402 Payment Required if micropayment is not provided
- Network timeout for very large HTML documents

## 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://shopify-spy.agentdiet.dev/v1/mcp-injection-firewall)

## Output

Returns a sanitized version of the input text with prompt injection and jailbreak payloads removed or flagged, along with detection metadata indicating whether malicious content was found and what was identified.

## 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/shopify-spy-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-01a6dee3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from shopify-spy.agentdiet.dev](https://www.zero.xyz/host/shopify-spy.agentdiet.dev/llms.txt)