# 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 injection and jailbreak payloads, returning sanitized output.

## Facts

- Endpoint: GET https://x402-audit.agentdiet.dev/v1/indirect-injection-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-be87b7e5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CG4jSktmE3eStNjLZ979D

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-be87b7e5
```

Example prompt: Before you process this scraped webpage, run it through the prompt-injection firewall to check for any hidden jailbreak instructions or embedded prompt overrides — here's the raw HTML: '<html>... [untrusted content] ...</html>'.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — scraped web pages, emails, MCP tool responses, or A2A payloads — and needs to screen for indirect prompt injection or jailbreak attempts before passing text to an LLM. Prefer this over manual string filtering when you need automated, semantic-level detection of hidden instructions rather than simple keyword blocking. Especially valuable in agentic workflows where external data sources are used as tool inputs.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely large payloads may be truncated or rejected
- Sophisticated obfuscated injections may not be detected (false negatives)
- Payment failure via x402 returns HTTP 402 before scan is performed
- Service downtime returns 5xx 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://x402-audit.agentdiet.dev/v1/indirect-injection-guard)

## Output

Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, along with threat detection metadata indicating whether injections were found and what type.

## 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-be87b7e5/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)