# 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/llm-jailbreak-defense?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-f6319e1d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_6avop6Dajg_zIrZlNY95w

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-f6319e1d -d '<json body>'
```

Example prompt: Before you summarize that webpage, scan its raw HTML for hidden prompt injections or jailbreak payloads and give me the sanitized version I can safely process.

## When to prefer this

Choose this endpoint when your AI agent needs to safely process content from untrusted external sources — scraped web pages, emails, third-party API responses, MCP tool outputs, or A2A payloads — before passing them to an LLM. It is especially valuable in agentic pipelines where indirect prompt injection could cause the agent to be hijacked or manipulated. Prefer this over generic content filters when you specifically need defense against LLM-targeted adversarial content rather than general spam or malware detection.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Payload too large may result in truncation or rejection
- False negatives: novel or obfuscated injection techniques may not be detected
- False positives: legitimate instruction-like text may be flagged as injections
- Service unavailability or payment failure returns 402 or 5xx error
- Non-text binary content may not be parsed correctly

## 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/llm-jailbreak-defense)

## Output

A response object containing the sanitized version of the input text with detected prompt injections removed, along with threat assessment signals indicating whether malicious content was found in the submitted payload.

## 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-f6319e1d/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)
