# AgentDiet Injection Guard

> AgentDiet Injection Guard is a paid API for AI agents from agentdiet.dev, paid per call via x402 or MPP, $0.005/call, status unknown (last checked 2026-10-21).

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

## Facts

- Endpoint: GET https://agentdiet.dev/v1/injection-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402, MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-injection-guard-0125551b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jrvOg4Npg9Fa79m5-A5ky

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-guard-0125551b
```

Example prompt: Before you process this scraped web page, run it through the injection guard to check for any hidden prompt injections or jailbreak instructions and give me the sanitized version.

## When to prefer this

Choose this endpoint when your agent needs to process content from untrusted external sources (web scraping, emails, third-party APIs, MCP responses, or A2A messages) before passing that content to an LLM. It is especially valuable in agentic pipelines where indirect prompt injection is a real attack vector and you need a lightweight, cheap ($0.005/call) pre-processing firewall step.

## Known failure modes

- Empty or missing 'text' query parameter returns an error
- Extremely long payloads may be truncated or rejected
- Novel or obfuscated injection patterns may evade detection
- Non-text binary content is not supported
- Rate limiting may occur under high request volume

## 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-guard)

## Output

Returns sanitized text with hidden prompt injections and jailbreak attempts removed or flagged, along with detection metadata indicating whether threats were found.

## 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-guard-0125551b/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)