# A2A Indirect Prompt-Injection & Jailbreak Firewall

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

Scans untrusted text, HTML, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized output.

## Facts

- Endpoint: POST https://domain-osint.agentdiet.dev/v1/llm-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: domain-osint.agentdiet.dev
- Website: https://domain-osint.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/domain-osint-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-9c30a2f9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ACrSRJQulCnqsdKOknvqk

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 domain-osint-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-9c30a2f9 -d '<json body>'
```

Example prompt: Before you summarize that webpage I just scraped, run the raw HTML through the LLM Guard firewall to check for any hidden prompt injections or jailbreak instructions embedded in the content.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — scraped HTML, emails, MCP tool responses, or A2A messages — that could contain adversarial prompt injection or jailbreak instructions. It is specifically designed for agent-to-agent and LLM security contexts, making it preferable over generic content moderation APIs when the threat model involves hidden instructions targeting language model behavior rather than user-facing harmful content.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Payload exceeding size limits may be rejected or truncated
- Payment failure (402) if x402 micropayment is not properly attached
- Transient upstream errors may return 5xx responses requiring retry with Idempotency-Key
- Extremely obfuscated injections may evade detection (false negatives)

## 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://domain-osint.agentdiet.dev/v1/llm-guard)

## Output

Returns a structured JSON object indicating whether the input text contained prompt injection or jailbreak payloads, along with a sanitized version of the text safe for downstream LLM consumption.

## 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/domain-osint-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-9c30a2f9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from domain-osint.agentdiet.dev](https://www.zero.xyz/host/domain-osint.agentdiet.dev/llms.txt)