# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from sec-intel.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-23).

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

## Facts

- Endpoint: POST https://sec-intel.agentdiet.dev/v1/prompt-injection-shield?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: sec-intel.agentdiet.dev
- Website: https://sec-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/sec-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-0f0c60be
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_deDU0K_Y6-8E7Pp8iuB7E

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 sec-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-0f0c60be -d '<json body>'
```

Example prompt: Before you process this scraped webpage content, run it through the prompt injection firewall to check for any hidden jailbreak instructions or adversarial injections — here's the raw HTML: [paste content].

## When to prefer this

Choose this endpoint when your AI agent is about to ingest or act on content from untrusted external sources — scraped web pages, inbound emails, third-party API responses, MCP tool outputs, or A2A payloads — and you need to ensure no hidden prompt injection or jailbreak instructions are embedded. Prefer this over generic content filters when the specific threat model is adversarial LLM manipulation rather than spam or NSFW content.

## Known failure modes

- Empty or whitespace-only text input returns validation error
- Extremely large payloads may be rejected or truncated
- Sophisticated obfuscated injections may evade detection
- Payment required (HTTP 402) if USDC balance is insufficient
- Timeout on very 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://sec-intel.agentdiet.dev/v1/prompt-injection-shield)

## Output

Returns a sanitized version of the input text with hidden prompt injections removed or neutralized, along with detection results indicating whether adversarial content was found and what type of threat was identified.

## 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/sec-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-0f0c60be/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sec-intel.agentdiet.dev](https://www.zero.xyz/host/sec-intel.agentdiet.dev/llms.txt)