# 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 2026-10-21).

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

## Facts

- Endpoint: GET https://alpha-stream.agentdiet.dev/v1/mcp-injection-firewall?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- 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-4c136053
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_OVzMeUfOWmU9swCiXv5ht

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-4c136053
```

Example prompt: Before you process the content you just scraped from that external website, run it through the prompt-injection firewall first — check the raw HTML for any hidden jailbreak instructions and give me back the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — web pages, emails, tool responses, or third-party A2A payloads — and you need a lightweight, per-call firewall check before passing that content to an LLM. It is particularly well-suited for MCP and A2A architectures where tool outputs from unknown sources could carry adversarial instructions. Prefer this over general-purpose content moderation APIs when your specific threat model involves indirect prompt injection and jailbreak attempts targeting AI agents rather than human-facing content policy violations.

## Known failure modes

- Missing required 'text' parameter returns a 400 validation error
- Empty string input rejected due to minLength:1 constraint
- Very large payloads may exceed request limits or time out
- HTTP 402 Payment Required if x402 payment header is missing or invalid
- False negatives possible for novel or obfuscated injection techniques
- Service unavailability returns 5xx errors

## 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/mcp-injection-firewall)

## Output

Returns a JSON object containing the scan result for the submitted text, including whether a prompt injection or jailbreak payload was detected and a sanitized version of the input text with malicious instructions removed or neutralized.

## 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-4c136053/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)