# AgentDiet Injection Firewall

> AgentDiet Injection Firewall is a paid API for AI agents from agentdiet.dev, paid per call via x402 or MPP, $0.005/call, status unknown (last checked 2026-10-20).

Scans untrusted text payloads (web pages, emails, MCP responses, A2A messages) for hidden prompt injections and jailbreak attempts, returning sanitized text

## Facts

- Endpoint: GET https://agentdiet.dev/v1/injection-firewall?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402, MPP
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-injection-firewall-ad4ad953
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Qh13K95U0yzFvLu3uGQ5o

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 agentdiet-injection-firewall-ad4ad953
```

Example prompt: Can you scan this web page text I just scraped for any hidden prompt injection or jailbreak instructions before I pass it to my AI pipeline? Here's the content: '[scraped HTML or text]'

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — web scrapes, emails, tool responses, or agent-to-agent messages — and you need a lightweight, pay-per-call firewall to detect and sanitize prompt injection or jailbreak attempts before they reach your LLM. Particularly valuable in A2A and MCP architectures where indirect injection via third-party content is a primary attack vector.

## Known failure modes

- Missing or empty 'text' query parameter returns an error
- Extremely long payloads may be truncated or rejected
- Novel or obfuscated injection techniques may evade detection
- Non-text binary content cannot be scanned
- Network timeouts on large payloads

## 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://agentdiet.dev/v1/injection-firewall)

## Output

Returns the sanitized version of the input text with prompt injection attempts and jailbreak instructions removed, along with detection signals indicating whether malicious content was found and what was stripped out

## 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/agentdiet-injection-firewall-ad4ad953/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentdiet.dev](https://www.zero.xyz/host/agentdiet.dev/llms.txt)