# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from preflight.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://preflight.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: preflight.agentdiet.dev
- Website: https://preflight.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-4902f92a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_QiSUu1xMbMSMa_ZEAIivy

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 preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-4902f92a -d '<json body>'
```

Example prompt: Before you process that scraped web page, run its content through the prompt injection firewall to make sure there are no hidden instructions trying to hijack you.

## When to prefer this

Choose this endpoint when your agent pipeline ingests untrusted external content — scraped web pages, forwarded emails, third-party MCP/A2A responses, or user-submitted text — and you need to sanitize it before passing it to an LLM. Prefer this over manual regex filtering or generic content moderation when the threat model specifically involves prompt injection and jailbreak vectors targeting AI agents.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Payload too large may result in a timeout or 413 error
- Ambiguous or obfuscated injections may not be detected with full confidence
- Payment not provided or insufficient USDC balance returns HTTP 402
- Network timeout on the endpoint returns a 5xx error

## 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://preflight.agentdiet.dev/v1/guard)

## Output

Returns a JSON object indicating whether the input text contains prompt injection or jailbreak content, along with sanitized text 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/preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-4902f92a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from preflight.agentdiet.dev](https://www.zero.xyz/host/preflight.agentdiet.dev/llms.txt)