# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from github-audit.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-23).

Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized output.

## Facts

- Endpoint: POST https://github-audit.agentdiet.dev/v1/system-prompt-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: github-audit.agentdiet.dev
- Website: https://github-audit.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/github-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-5c7bf5e6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0zk3e1tbpV6sJTr_urq5L

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 github-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-5c7bf5e6 -d '<json body>'
```

Example prompt: Before you process this scraped webpage content, can you run it through the prompt-injection firewall to check for any hidden jailbreak or prompt-injection payloads and give me the sanitized version?

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, user emails, third-party API or MCP responses, or A2A messages — and you need a dedicated firewall step before that content influences agent behavior. It is specifically designed for the indirect prompt-injection threat model where malicious instructions are hidden in data rather than typed directly by a user, making it more appropriate than generic content moderation tools.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Payloads exceeding length limits may be rejected
- Payment required (HTTP 402) if x402 USDC micropayment is not included
- Ambiguous or highly obfuscated injections may not be caught with full confidence
- Network timeouts on very large inputs

## 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://github-audit.agentdiet.dev/v1/system-prompt-guard)

## Output

Returns a structured object indicating whether a prompt injection or jailbreak attempt was detected in the input, along with sanitized text with any malicious instructions removed or flagged, enabling safe downstream consumption by an AI agent.

## 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/github-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-5c7bf5e6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from github-audit.agentdiet.dev](https://www.zero.xyz/host/github-audit.agentdiet.dev/llms.txt)