# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from shopify-intel.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-23).

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

## Facts

- Endpoint: POST https://shopify-intel.agentdiet.dev/v1/workflows/rag-context-sanitizer?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: shopify-intel.agentdiet.dev
- Website: https://shopify-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/shopify-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c41fd73e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_lz9HMaT8t3faxAYwfX-Zb

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-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c41fd73e -d '<json body>'
```

Example prompt: Before you use that scraped web page as context, run it through the prompt-injection firewall and give me the sanitized version — I don't want any hidden jailbreak instructions sneaking into your context window.

## When to prefer this

Choose this endpoint when your AI agent must consume content from untrusted external sources — scraped web pages, third-party emails, external MCP tool responses, or A2A agent payloads — before using them as RAG context or passing them downstream. It is specifically designed for agent-to-agent and human-to-agent pipeline security, not generic content moderation.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely large payloads may time out or be rejected
- Highly obfuscated injections using novel encoding may evade detection
- Service unavailability returns 5xx errors; use the Idempotency-Key header to safely retry
- Non-text binary content or non-UTF-8 encoded input may cause parsing failures

## 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-intel.agentdiet.dev/v1/workflows/rag-context-sanitizer)

## Output

Returns a sanitized version of the input text with any detected prompt injection payloads or jailbreak instructions neutralized or flagged, making it safe to pass into an AI agent's context window or RAG pipeline.

## 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-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c41fd73e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from shopify-intel.agentdiet.dev](https://www.zero.xyz/host/shopify-intel.agentdiet.dev/llms.txt)