# 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 output.

## Facts

- Endpoint: POST https://onchain-risk.agentdiet.dev/v1/prompt-guard?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-25d10dc7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MK2YykBBwCKkMUA0AKk15

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-25d10dc7 -d '<json body>'
```

Example prompt: Before you process that web page content, scan it for hidden prompt injections or jailbreak instructions and give me the sanitized version that's safe to use.

## When to prefer this

Choose this endpoint when your AI agent is about to consume content from untrusted external sources — web pages, emails, third-party APIs, MCP tool responses, or A2A payloads — and you need a dedicated firewall layer to strip or flag hidden prompt injection and jailbreak instructions before they reach your agent's context window. Prefer this over general-purpose text sanitizers when the threat model is specifically adversarial LLM manipulation rather than XSS or SQL injection.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely large payloads may exceed input size limits
- Payment required (HTTP 402) if x402 USDC micropayment is not provided
- Ambiguous or obfuscated injections may not be detected with 100% accuracy
- Non-text binary content may produce unexpected 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://onchain-risk.agentdiet.dev/v1/prompt-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 detection metadata indicating whether malicious content was found.

## 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/onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-25d10dc7/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)
