# 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 text.

## Facts

- Endpoint: GET https://workflows.agentdiet.dev/v1/prompt-injection-shield?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-ca3eebdf
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VET-8tJGz8Cq0FkCJGZmk

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-ca3eebdf
```

Example prompt: Before you process that scraped web page, run it through the prompt-injection firewall to check for hidden instructions or jailbreak payloads and give me the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent needs to safely consume content from untrusted external sources — scraped web pages, inbound emails, third-party MCP/A2A tool responses — before passing that content to an LLM. It is especially valuable in multi-agent pipelines where one agent's output becomes another's input, creating indirect injection attack surfaces. Prefer it over generic content filters when the specific threat model is adversarial prompt injection or jailbreak payloads targeting LLM behavior.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long text payloads may be truncated or rejected
- Service unavailable (502/503) if the upstream firewall model is down
- Payment required (402) if no valid x402 micropayment header is provided
- False negatives: novel or obfuscated injection techniques may not be detected

## 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/prompt-injection-shield)

## Output

Returns a JSON object containing the scan result for the submitted text, including detection of any hidden prompt injection or jailbreak payloads 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-ca3eebdf/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)