# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from serp-extract.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 injections and jailbreak attempts, returning sanitized output.

## Facts

- Endpoint: POST https://serp-extract.agentdiet.dev/v1/llm-jailbreak-defense?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: serp-extract.agentdiet.dev
- Website: https://serp-extract.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/serp-extract-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-bcecaf0c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ttBlhZuqeHRS--EqQsMWo

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 serp-extract-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-bcecaf0c -d '<json body>'
```

Example prompt: Before you process that scraped web page, run it through the jailbreak firewall to check for any hidden prompt injection instructions and give me the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — web pages, emails, MCP tool responses, or A2A agent payloads — and you need to sanitize that content before passing it to an LLM. Prefer this over generic content filters when you specifically need to detect adversarial prompt injection and jailbreak patterns targeting language models, particularly in agentic and multi-agent workflows.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely large payloads may time out or be rejected
- False negatives possible — novel or obfuscated injections may not be detected
- False positives possible — legitimate instruction-like content may be flagged
- Service unavailability returns 5xx errors; use Idempotency-Key header for safe retries

## 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://serp-extract.agentdiet.dev/v1/llm-jailbreak-defense)

## Output

Returns a JSON object containing the sanitized version of the input text with hidden prompt injections and jailbreak payloads removed or flagged, along with detection metadata indicating whether malicious content was found.

## 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/serp-extract-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-bcecaf0c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from serp-extract.agentdiet.dev](https://www.zero.xyz/host/serp-extract.agentdiet.dev/llms.txt)