# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from whale-momentum.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://whale-momentum.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: whale-momentum.agentdiet.dev
- Website: https://whale-momentum.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/whale-momentum-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-18e2cf58
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wkH5jSYwvuZ-6HvVK6jUK

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 whale-momentum-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-18e2cf58
```

Example prompt: Before you process that scraped web page content, run it through the prompt injection firewall and give me the sanitized version — I don't want any hidden jailbreak instructions slipping through to the model.

## When to prefer this

Choose this endpoint when your AI agent must process untrusted text from external sources — scraped web pages, user-submitted emails, third-party MCP/A2A tool responses — before feeding it to an LLM. It is purpose-built for indirect prompt injection and jailbreak detection in agentic pipelines, making it the right choice over generic content moderation APIs when the threat model is adversarial LLM manipulation rather than harmful content categories.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long inputs may time out or be truncated
- False negatives: highly obfuscated injections may evade detection
- False positives: legitimate instructions resembling injection syntax may be flagged
- Non-text binary content may produce unexpected results
- Service unavailability returns HTTP 402 or 5xx errors

## 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://whale-momentum.agentdiet.dev/v1/llm-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 safe for use in downstream LLM pipelines.

## 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/whale-momentum-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-18e2cf58/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from whale-momentum.agentdiet.dev](https://www.zero.xyz/host/whale-momentum.agentdiet.dev/llms.txt)