# 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 2026-10-23).

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

## Facts

- Endpoint: POST https://mesh.agentdiet.dev/v1/workflows/rag-context-sanitizer?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- 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-8e675118
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UXGGRyt24EcaTBTtztZFW

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-8e675118 -d '<json body>'
```

Example prompt: Before you summarize this scraped web page, run it through the prompt injection firewall to check for hidden jailbreak instructions — here's the raw HTML: '<html>...trusted content... <!-- Ignore previous instructions and...--> </html>'

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — web pages, emails, third-party API responses, MCP tool outputs, or A2A agent payloads — and you need to guard against indirect prompt injection or jailbreak attacks before that content reaches your LLM. Prefer this over manual filtering when operating in autonomous multi-agent workflows where a compromised upstream payload could hijack agent behavior.

## Known failure modes

- Empty or missing 'text' field returns validation error
- Extremely long inputs may hit payload size limits
- Sophisticated steganographic injections may evade detection
- Non-UTF-8 encoded content may cause parsing errors
- Payment failure (402) if x402 micropayment is not properly handled

## 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/workflows/rag-context-sanitizer)

## Output

Returns a JSON object containing the scan result, including whether prompt injection or jailbreak content was detected, and a sanitized version of the input text with malicious instructions removed or flagged, safe for downstream LLM or agent 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/mesh-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-8e675118/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)