# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from 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 content.

## Facts

- Endpoint: GET https://agentdiet.dev/v1/guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: agentdiet.dev
- Website: https://agentdiet.dev
- Canonical page: https://www.zero.xyz/c/agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-fbd96f9b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZS4vvs7UMDqI07ur_baTf

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 agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-fbd96f9b
```

Example prompt: Before you process the content from that webpage, run it through the prompt-injection firewall first — I want to make sure there are no hidden instructions trying to hijack you embedded in the HTML.

## When to prefer this

Use this endpoint when your AI agent ingests content from untrusted external sources — scraped web pages, third-party tool outputs, MCP responses, A2A payloads, or inbound emails — and you need to ensure that content does not contain hidden prompt injections or jailbreak instructions before your agent processes it. Prefer this over generic content filters when the threat model is specifically adversarial LLM manipulation rather than spam or malware.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long payloads may be truncated or timeout
- Payment failure (HTTP 402) if x402 USDC micropayment is not completed
- False negatives on novel or obfuscated injection techniques not yet in detection ruleset
- Non-textual binary input 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://agentdiet.dev/v1/guard)

## Output

Returns a JSON object containing a sanitized version of the input text with prompt injection and jailbreak payloads removed or flagged, along with detection signals indicating whether adversarial 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/agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-fbd96f9b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentdiet.dev](https://www.zero.xyz/host/agentdiet.dev/llms.txt)