# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from prompt-guard.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-21).

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

## Facts

- Endpoint: GET https://prompt-guard.agentdiet.dev/paid?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: prompt-guard.agentdiet.dev
- Website: https://prompt-guard.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/prompt-guard-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-f857d897
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WuJNZT_h7wUwxalH9Pz25

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 prompt-guard-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-f857d897
```

Example prompt: Before you process this webpage I just scraped, run the text through the prompt injection firewall to check for any hidden instructions trying to hijack you, then give me the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent is processing untrusted external content — scraped web pages, third-party API responses, MCP tool outputs, A2A payloads, or user-submitted emails — and you need to detect and strip hidden prompt injection or jailbreak instructions before passing the content to an LLM. Prefer this over general content moderation APIs when the threat model is specifically adversarial prompt manipulation targeting AI agents rather than harmful human-facing content.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long payloads may be truncated or rejected
- Payment not completed via x402 returns HTTP 402 requiring USDC micropayment
- False negatives possible for novel or obfuscated injection techniques
- Service downtime returns 5xx errors with no sanitized output

## 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://prompt-guard.agentdiet.dev/paid)

## Output

Returns a JSON object containing the scan result for the submitted text, including whether prompt injection or jailbreak content was detected and a sanitized version of the input text safe for downstream LLM 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/prompt-guard-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-f857d897/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from prompt-guard.agentdiet.dev](https://www.zero.xyz/host/prompt-guard.agentdiet.dev/llms.txt)