# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from mcp-security.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown.

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

## Facts

- Endpoint: POST https://mcp-security.agentdiet.dev/v1/workflows/rag-context-sanitizer?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Activations on Zero: 0
- Provider: mcp-security.agentdiet.dev
- Website: https://mcp-security.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-71cdf838
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hAYlEOgA3X8mr0ZZsTb5h

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 mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-71cdf838 -d '<json body>'
```

Example prompt: Before you use this web page content to answer my question, scan it for hidden prompt injections or jailbreak instructions and give me the sanitized version — the raw HTML is: '<html>...untrusted content here...</html>'.

## When to prefer this

Choose this endpoint when your agent needs to process text from untrusted external sources — web scrapes, emails, third-party tool/MCP responses, or A2A payloads — before feeding them into an LLM context. Especially valuable in agentic pipelines where indirect prompt injection could hijack agent behavior. Prefer this over generic content filters when you specifically need protection against LLM-targeted adversarial instructions rather than general spam or malware.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Extremely long inputs may exceed processing limits
- Novel or obfuscated injection techniques may not be detected
- Non-textual binary content may not be parseable
- Service unavailability returns a 5xx error; idempotency key allows safe retries

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

## Output

Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, allowing the calling agent to safely use the content in downstream LLM processing.

## 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/mcp-security-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-71cdf838/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mcp-security.agentdiet.dev](https://www.zero.xyz/host/mcp-security.agentdiet.dev/llms.txt)