# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from onchain-risk.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 injections and jailbreak attempts, returning sanitized content.

## Facts

- Endpoint: GET https://onchain-risk.agentdiet.dev/v1/mcp-security?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-11-21
- Activations on Zero: 0
- Provider: onchain-risk.agentdiet.dev
- Website: https://onchain-risk.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-a63eed9d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_NR3FCLL05Wm2pXeqgekZU

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 onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-a63eed9d
```

Example prompt: Before you process this webpage content, run it through the prompt injection firewall to check for any hidden jailbreak or prompt manipulation attempts: '<paste raw HTML or text here>'

## When to prefer this

Choose this endpoint when your AI agent needs to process content from untrusted external sources — scraped web pages, third-party emails, external MCP tool responses, or user-submitted text — before incorporating that content into its reasoning chain. It is specifically designed for the A2A and MCP ecosystem, making it ideal for multi-agent pipelines where one agent's output becomes another's input. Prefer this over generic content filters when you need prompt-injection-specific detection rather than general spam or malware scanning.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely large payloads may be truncated or rejected
- Payment required (HTTP 402) if x402 micropayment header is missing or invalid
- Ambiguous or heavily obfuscated injections may not be detected with full confidence
- Cursor-based pagination may return empty pages if result set is exhausted

## 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://onchain-risk.agentdiet.dev/v1/mcp-security)

## Output

Returns a structured object containing detected prompt injection or jailbreak findings, flagged suspicious segments, and a sanitized version of the input text safe for downstream agent consumption. Pagination supported via cursor and limit parameters.

## 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"
  },
  "limit": {
   "type": "integer",
   "default": 20,
   "maximum": 100,
   "minimum": 1,
   "description": "Maximum number of items to return per page (1-100)"
  },
  "cursor": {
   "type": "string",
   "description": "Opaque pagination cursor for fetching the next page"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-a63eed9d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from onchain-risk.agentdiet.dev](https://www.zero.xyz/host/onchain-risk.agentdiet.dev/llms.txt)
