# A2A Indirect Prompt-Injection & Jailbreak Firewall

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

## Facts

- Endpoint: GET https://agentdiet.dev/v1/rag-poison-shield?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: agentdiet.dev
- Website: https://agentdiet.dev
- Canonical page: https://www.zero.xyz/c/agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-3c2f5e38
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_37aTfEzaFkuxMVb7RanKv

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 agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-3c2f5e38
```

Example prompt: Before you process that webpage I just scraped, can you run it through the RAG poison shield to check for any hidden prompt injections or jailbreak payloads and give me the sanitized version?

## When to prefer this

Use this endpoint whenever your AI agent must consume untrusted external content — scraped web pages, emails, MCP/A2A tool responses, or RAG documents — before processing. It is specifically designed for the agent-to-agent and retrieval-augmented generation security context, making it preferable over generic content filters when the threat model is indirect prompt injection or jailbreak payloads embedded in external data sources.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long inputs may be truncated or rejected
- False negatives: sophisticated obfuscated injections may not be caught
- False positives: legitimate content resembling injection syntax may be flagged
- Service unavailability returns HTTP 402 or 5xx errors
- Malformed HTML or binary content may produce unexpected sanitization results

## 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://agentdiet.dev/v1/rag-poison-shield)

## Output

Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak content removed or flagged, helping agents safely consume untrusted external data.

## 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/agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-3c2f5e38/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentdiet.dev](https://www.zero.xyz/host/agentdiet.dev/llms.txt)