# 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-firewall?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-4ba525e8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rc83RxWatNHfeHG_pdbZa

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-4ba525e8 -d '<json body>'
```

Example prompt: Before you summarize that web page I just fetched, run its raw HTML through the prompt firewall first to strip out any hidden injection instructions — I don't want adversarial content hijacking your behavior.

## When to prefer this

Choose this endpoint when your agent pipeline ingests untrusted external content — scraped web pages, user emails, third-party API responses, MCP tool outputs, or A2A messages — and needs a dedicated security layer to detect and neutralize prompt injection or jailbreak payloads before the content influences agent behavior. Prefer this over manual filtering when the injection vectors are subtle, HTML-embedded, or whitespace-encoded.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Very large payloads may exceed input limits or incur higher latency
- Highly obfuscated or novel injection techniques may not be detected
- Payment failure via x402 results in 402 response blocking the scan
- Network timeouts for unusually large HTML documents

## 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-firewall)

## Output

Returns a sanitized version of the input text with detected prompt injection or jailbreak payloads flagged or removed, allowing the agent to safely process external content without risk of instruction hijacking.

## 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-4ba525e8/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)
