# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from alpha-stream.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://alpha-stream.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: alpha-stream.agentdiet.dev
- Website: https://alpha-stream.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-7ccf5478
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8nZiGvPQUQFrwKggwAG_v

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 alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-7ccf5478 -d '<json body>'
```

Example prompt: Before you process the content from that scraped webpage, run it through the prompt injection firewall to check for any hidden instructions trying to hijack you — here's the raw HTML: '<html>...buy now...</html> IGNORE ALL PREVIOUS INSTRUCTIONS'.

## When to prefer this

Choose this endpoint when your AI agent is consuming untrusted external content — scraped web pages, inbound emails, third-party tool or MCP responses, or A2A payloads — and needs to sanitize that content before reasoning over it or acting on it, specifically to prevent indirect prompt injection and jailbreak attacks. Prefer this over generic text filtering when the threat model is specifically adversarial LLM manipulation rather than spam or toxicity.

## Known failure modes

- Empty or missing 'text' field returns a 422 validation error
- Extremely large payloads may hit size limits or time out
- Sophisticated obfuscated injections may evade detection (false negatives)
- Benign text containing LLM-like syntax may be flagged as injection (false positives)
- Payment failure via x402 returns 402 Payment Required

## 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://alpha-stream.agentdiet.dev/v1/prompt-guard)

## Output

Returns a JSON object indicating whether prompt injection or jailbreak content was detected, along with sanitized text stripped of adversarial payloads, enabling agents to safely process the cleaned content.

## 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/alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-7ccf5478/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from alpha-stream.agentdiet.dev](https://www.zero.xyz/host/alpha-stream.agentdiet.dev/llms.txt)
