# A2A Indirect Prompt-Injection & Jailbreak Firewall

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

## Facts

- Endpoint: GET https://mesh.agentdiet.dev/v1/llm-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: mesh.agentdiet.dev
- Website: https://mesh.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/mesh-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-a6ddeeac
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FAL6u8GoGnCxLWfvAVCGi

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 mesh-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-a6ddeeac
```

Example prompt: Before you summarize that webpage, can you run it through the LLM-Guard firewall first to check if it contains any hidden prompt injection or jailbreak instructions embedded in the content?

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — web pages, emails, MCP/A2A tool responses, or user-submitted text — before passing it to an LLM. It is specifically designed for the A2A/MCP agent security use case, making it more appropriate than generic content filters when defending against indirect prompt injection, jailbreak payloads hidden in HTML or markdown, or adversarial instructions embedded in tool outputs.

## Known failure modes

- Empty or missing 'text' parameter returns validation error
- Very large payloads may timeout or be truncated
- Obfuscated or encoded injections may evade detection
- Payment required (HTTP 402) if x402 payment header not provided
- False positives may flag legitimate instructional text as injections
- Non-English injection attempts may have lower detection accuracy

## 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://mesh.agentdiet.dev/v1/llm-guard)

## Output

Returns a structured object indicating whether the input text contains prompt injection or jailbreak payloads, along with sanitized text with malicious instructions removed or flagged, enabling the agent to safely proceed with clean 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/mesh-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-a6ddeeac/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mesh.agentdiet.dev](https://www.zero.xyz/host/mesh.agentdiet.dev/llms.txt)