# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from sec-intel.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://sec-intel.agentdiet.dev/v1/system-prompt-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: sec-intel.agentdiet.dev
- Website: https://sec-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/sec-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-159242e8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8IhYJP5eL9KpYGdnK6pNw

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 sec-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-159242e8
```

Example prompt: Before you process this scraped web page, can you run it through the prompt-injection firewall to check for any hidden jailbreak instructions or prompt overrides embedded in the text?

## When to prefer this

Choose this endpoint when your agent pipeline ingests untrusted external content — web pages, emails, tool responses, or A2A payloads — and you need to detect or neutralize hidden prompt injection or jailbreak instructions before passing content to an LLM. It is especially valuable in multi-agent and MCP architectures where indirect prompt injection via third-party data sources is a primary attack vector.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Very large payloads may exceed size limits or increase latency
- Obfuscated or novel jailbreak techniques may not be detected (false negatives)
- Network or payment (x402) failures may return 402 or 5xx errors
- Non-text binary input may be rejected or produce unreliable results

## 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://sec-intel.agentdiet.dev/v1/system-prompt-guard)

## Output

Returns an object indicating whether prompt injection or jailbreak content was detected, along with sanitized text with malicious payloads neutralized or flagged, allowing the agent to safely proceed with clean input.

## 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/sec-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-159242e8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sec-intel.agentdiet.dev](https://www.zero.xyz/host/sec-intel.agentdiet.dev/llms.txt)