# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from mcp-security.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://mcp-security.agentdiet.dev/v1/prompt-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: mcp-security.agentdiet.dev
- Website: https://mcp-security.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-b58431aa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yCNzJ2SPdKW2MyAJMsTM8

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 mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-b58431aa
```

Example prompt: Before you process that scraped web page, run the raw HTML through the prompt-guard firewall to check for hidden prompt injections or jailbreak payloads and give me the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent ingests content from untrusted external sources — web scraping, email processing, third-party MCP/A2A tool responses, or user-submitted input — and you need a dedicated firewall layer to detect and strip hidden prompt injections before they can hijack your agent's behavior. Prefer this over generic text filters when you specifically need adversarial LLM instruction detection (not just spam or malware scanning).

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long payloads may be truncated or rejected
- False negatives possible on novel or highly obfuscated injection techniques
- Payment required error (402) if x402 USDC payment not included
- Non-text binary content may not be parseable

## 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://mcp-security.agentdiet.dev/v1/prompt-guard)

## Output

Returns a structured object indicating whether prompt injection or jailbreak content was detected, along with sanitized text with malicious instructions removed or flagged, allowing the calling agent to safely continue 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/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-b58431aa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mcp-security.agentdiet.dev](https://www.zero.xyz/host/mcp-security.agentdiet.dev/llms.txt)