# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from email-verify.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-11-21).

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

## Facts

- Endpoint: POST https://email-verify.agentdiet.dev/v1/rag-poison-shield?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-11-21
- Activations on Zero: 0
- Provider: email-verify.agentdiet.dev
- Website: https://email-verify.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/email-verify-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-db1a858e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_a3rRlHBVoMK9glwMUr5gY

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 email-verify-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-db1a858e -d '<json body>'
```

Example prompt: Before you process that scraped webpage content, run it through the RAG Poison Shield to check for any hidden prompt injections or jailbreak instructions embedded in the HTML — here's the raw text: [paste untrusted content].

## When to prefer this

Choose this endpoint when your AI agent ingests content from untrusted external sources — web scraping, email processing, RAG pipelines, MCP tool responses, or A2A payloads — and you need a dedicated firewall to detect and neutralize prompt-injection and jailbreak attacks before the content reaches your LLM. Prefer this over manual regex filtering or generic moderation APIs when the threat model specifically involves adversarial instruction injection targeting AI agent behavior.

## Known failure modes

- Empty or too-short text input returns a validation error
- Overly long payloads may be truncated or rejected
- False negatives possible for novel obfuscated injection techniques
- Service unavailability returns HTTP 402/503 if payment or quota issues arise
- Malformed JSON input returns a 400 bad request 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://email-verify.agentdiet.dev/v1/rag-poison-shield)

## Output

Returns an object containing the detection verdict, identified injection or jailbreak patterns found in the input, and a sanitized version of the text with malicious instructions removed or neutralized, enabling safe downstream LLM processing.

## 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/email-verify-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-db1a858e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from email-verify.agentdiet.dev](https://www.zero.xyz/host/email-verify.agentdiet.dev/llms.txt)
