# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from preflight.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 injections and jailbreak attempts, returning sanitized text.

## Facts

- Endpoint: POST https://preflight.agentdiet.dev/v1/workflows/rag-context-sanitizer?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: preflight.agentdiet.dev
- Website: https://preflight.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-845ca999
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JoCMJH24ix_TgIp2QimyN

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 preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-845ca999 -d '<json body>'
```

Example prompt: Before you summarize that scraped web page, run the raw HTML through the prompt-injection firewall first and give me the sanitized version — I don't want hidden instructions hijacking you.

## When to prefer this

Choose this endpoint when your agent pipeline ingests untrusted external content — scraped HTML, emails, MCP/A2A tool responses, or RAG chunks — and you need an automated firewall layer to strip hidden prompt injections before the content reaches your LLM. Prefer this over manual filtering or regex-based approaches when the attack surface includes sophisticated jailbreak payloads or white-text/invisible injection techniques. Particularly valuable for multi-agent systems where one agent's output is consumed by another.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely large payloads may exceed processing limits or time out
- False negatives are possible — novel or obfuscated injection techniques may not be detected
- Payment not settled (HTTP 402) blocks execution if USDC micropayment via x402 is required
- Non-text binary content (e.g., raw images) is not meaningful input and may yield empty sanitization

## 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://preflight.agentdiet.dev/v1/workflows/rag-context-sanitizer)

## Output

Returns a sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, along with metadata indicating whether threats were found and what was cleaned.

## 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/preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-845ca999/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from preflight.agentdiet.dev](https://www.zero.xyz/host/preflight.agentdiet.dev/llms.txt)