# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from x402-audit.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 content.

## Facts

- Endpoint: GET https://x402-audit.agentdiet.dev/v1/guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: x402-audit.agentdiet.dev
- Website: https://x402-audit.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/x402-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cd2da2c7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_h3W3jTglhS8eKTlxeVYvu

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 x402-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cd2da2c7
```

Example prompt: Before you process that web page I just fetched, can you run its raw HTML through the prompt injection firewall to make sure there are no hidden adversarial instructions embedded in it?

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — web scraping, email ingestion, third-party MCP/A2A tool responses — and you need a dedicated firewall layer to detect and strip hidden prompt injections before your LLM processes the content. Prefer this over generic text sanitization when the threat model specifically involves adversarial LLM manipulation rather than XSS or SQL injection.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long payloads may be truncated or rejected
- False negatives possible for novel or obfuscated injection techniques
- HTTP 402 payment required if x402 payment header is not included
- Non-text binary content may not be correctly parsed

## 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://x402-audit.agentdiet.dev/v1/guard)

## Output

Returns a structured object indicating whether a prompt injection or jailbreak payload was detected in the input text, along with a sanitized version of the content 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/x402-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cd2da2c7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-audit.agentdiet.dev](https://www.zero.xyz/host/x402-audit.agentdiet.dev/llms.txt)