# 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-injection and jailbreak attacks, returning sanitized output.

## Facts

- Endpoint: GET https://sec-intel.agentdiet.dev/v1/llm-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-cb9779a7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_p5yhGlkC8NwxlQJ2nDl3s

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-cb9779a7
```

Example prompt: Before you process this scraped webpage content, run it through the LLM Guard firewall to check for hidden prompt injection or jailbreak payloads — here's the raw HTML: [paste content here].

## When to prefer this

Choose this endpoint when your agent is consuming text from untrusted external sources — scraped web pages, user emails, third-party API/MCP responses, or A2A payloads — before passing them into an LLM context window. Especially valuable in autonomous agent pipelines where a compromised tool response could hijack agent behavior. Prefer this over generic content moderation endpoints when the specific threat model is prompt injection and jailbreak rather than hate speech or NSFW content.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long inputs may be truncated or rejected
- False negatives possible for novel/obfuscated injection techniques
- Network timeout if the service is unavailable
- 402 Payment Required if USDC micropayment is not included or insufficient

## 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/llm-guard)

## Output

Returns a structured object indicating whether the input text contains prompt-injection or jailbreak content, along with sanitized text safe for downstream LLM consumption. May include threat classification, flagged spans, and a clean version of the 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-cb9779a7/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)