# 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 injection and jailbreak attacks, returning sanitized output.

## Facts

- Endpoint: POST https://mcp-security.agentdiet.dev/v1/jailbreak-scan?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-8349a439
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tKJzwfVbBn6cFLMAeUGcZ

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-8349a439 -d '<json body>'
```

Example prompt: Before you process this scraped webpage content, run it through the jailbreak firewall to check for hidden prompt injections and give me the sanitized version: [paste raw HTML or text here].

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, third-party API responses, MCP tool outputs, inbound emails, or user-submitted text — and you need a dedicated security layer to detect and strip indirect prompt injection or jailbreak payloads before they reach your LLM context. Prefer this over general content moderation APIs when the threat model is specifically adversarial prompt manipulation targeting AI agents rather than toxic or inappropriate content.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely long payloads may exceed input limits or time out
- False negatives may occur for highly obfuscated or novel injection techniques
- Non-text binary content may not be parsed correctly
- Payment/402 failure if x402 USDC micropayment is not completed

## 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/jailbreak-scan)

## Output

Returns a JSON object containing the scan result, including whether a prompt injection or jailbreak payload was detected and a sanitized version of the input text with malicious instructions stripped 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/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-8349a439/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)