# 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, web pages, emails, MCP responses, or A2A payloads for hidden prompt-injection and jailbreak attacks, returning sanitized content.

## Facts

- Endpoint: POST https://mesh.agentdiet.dev/v1/prompt-shield?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-10fb12e6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_PkGCF8krLGGJhz_b7MSW3

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-10fb12e6 -d '<json body>'
```

Example prompt: Before passing this scraped webpage content to the next step in the pipeline, run it through the prompt-shield firewall to detect and strip any hidden prompt injection or jailbreak instructions: [paste untrusted text here].

## When to prefer this

Choose this endpoint when your agent pipeline ingests any untrusted external content — scraped web pages, inbound emails, third-party API responses, or MCP/A2A tool outputs — and you need a lightweight, pay-per-call firewall check before that content influences LLM behavior. Prefer it over rolling your own regex heuristics or relying on the LLM itself to resist injection, especially in autonomous multi-agent workflows where a single compromised payload could hijack the entire chain.

## Known failure modes

- Empty or whitespace-only 'text' field triggers a 422 validation error
- Extremely long inputs may hit payload size limits
- Payment not attached or insufficient funds returns HTTP 402
- Ambiguous or highly obfuscated injections may not be detected with full confidence
- Network timeout on large HTML documents

## 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/prompt-shield)

## Output

Returns a JSON object indicating whether the input text contained prompt-injection or jailbreak payloads, along with a sanitized version of the text 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-10fb12e6/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)