# 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.

## Facts

- Endpoint: POST https://shopify-intel.agentdiet.dev/v1/llm-guard?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-4a33810a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8fkOYmUNBJH7DnCMa_PGf

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-4a33810a -d '<json body>'
```

Example prompt: Before you process this scraped webpage content, run it through the prompt injection firewall to check for any hidden jailbreak instructions or adversarial prompts embedded in it — here's the raw text: [paste content].

## When to prefer this

Choose this endpoint when your AI agent needs to process content from untrusted external sources — web pages, emails, user-submitted text, or third-party tool responses — before passing that content to an LLM. It is purpose-built for the agent-security use case of indirect prompt injection and jailbreak detection, unlike general content moderation APIs that focus on hate speech or NSFW content. Prefer it in agentic pipelines where an adversary could craft a web page or API response to hijack agent behavior.

## Known failure modes

- Empty or missing 'text' field returns a validation error
- Extremely large payloads may exceed size limits or time out
- Obfuscated or novel injection techniques may not be detected (evasion)
- Non-text binary content may fail to parse correctly
- Rate limiting or payment failure (HTTP 402) if USDC balance is insufficient

## 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/llm-guard)

## Output

Returns a JSON object indicating whether prompt injection or jailbreak content was detected in the input, along with a sanitized version of the text with malicious instructions removed or flagged.

## 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-4a33810a/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)