# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from mcp-security.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 output.

## Facts

- Endpoint: POST https://mcp-security.agentdiet.dev/v1/guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: mcp-security.agentdiet.dev
- Website: https://mcp-security.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-05fd5e44
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WLWsIGdtpk3usdrhOYiCO

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 mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-05fd5e44 -d '<json body>'
```

Example prompt: Before you process the content from that external website, can you run it through the prompt injection firewall to check for any hidden jailbreak instructions or adversarial text embedded in it?

## When to prefer this

Use this endpoint whenever your agent is about to consume content from an untrusted external source — scraped web pages, user-submitted emails, third-party MCP or A2A tool responses — before passing that content to an LLM or downstream agent step. It is specifically designed for the indirect prompt injection threat vector (adversarial instructions embedded in data, not direct user input) and supports idempotent retries via Idempotency-Key header.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely long payloads may hit size or timeout limits
- False negatives: novel or obfuscated injection techniques may not be caught
- Payment not completed (HTTP 402) blocks the request if x402 funds are unavailable
- Ambiguous or benign-looking injections may be incorrectly flagged as safe

## 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://mcp-security.agentdiet.dev/v1/guard)

## Output

Returns a JSON object containing the scan result for the submitted text, including whether a prompt injection or jailbreak payload was detected and the sanitized version of the input safe for downstream agent 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/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-05fd5e44/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mcp-security.agentdiet.dev](https://www.zero.xyz/host/mcp-security.agentdiet.dev/llms.txt)