# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from workflows.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://workflows.agentdiet.dev/v1/indirect-injection-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: workflows.agentdiet.dev
- Website: https://workflows.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-56dbcfd0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JmFGkJLVHi9Pt65JVL_-2

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 workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-56dbcfd0
```

Example prompt: Before you process that scraped webpage, run it through the prompt injection firewall first — scan this HTML for any hidden jailbreak instructions or indirect prompt injection attempts and give me the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent is consuming content from untrusted external sources — scraped web pages, inbound emails, third-party API responses, MCP tool outputs, or A2A payloads — and you need a dedicated security layer to catch indirect prompt injection or jailbreak attempts before that content reaches your LLM. It is purpose-built for agentic pipelines and supports x402 micropayment and MCP protocols natively, making it ideal for autonomous agent architectures that need per-call, low-cost security screening without running a self-hosted firewall.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long payloads may hit query string length limits due to GET method — content should be URL-encoded properly
- Payment required (HTTP 402) if x402 micropayment headers are not provided or balance is insufficient
- False negatives are possible for highly obfuscated or novel injection techniques not yet in the firewall ruleset
- Malformed HTML may affect parsing accuracy of the injection scan

## 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://workflows.agentdiet.dev/v1/indirect-injection-guard)

## Output

Returns a JSON object containing the scan result for the submitted text, including whether prompt injection or jailbreak content was detected and a sanitized version of the input text safe for downstream 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/workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-56dbcfd0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from workflows.agentdiet.dev](https://www.zero.xyz/host/workflows.agentdiet.dev/llms.txt)