# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from cve-intel.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-23).

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

## Facts

- Endpoint: POST https://cve-intel.agentdiet.dev/v1/llm-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Provider: cve-intel.agentdiet.dev
- Website: https://cve-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/cve-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-ecd0430f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_05gQGW5Auo6xxBmvXvPtk

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 cve-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-ecd0430f -d '<json body>'
```

Example prompt: Before you process that scraped webpage content, run it through the prompt-injection firewall to check for any hidden jailbreak instructions or adversarial prompts embedded in the text.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, user-submitted inputs, third-party API responses, MCP tool outputs, or email bodies — and you need to guard against indirect prompt injection attacks before passing that content to an LLM. Ideal for agentic systems that autonomously browse the web, call external tools, or process user-supplied documents where adversarial content could hijack agent behavior.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Payloads that are extremely large may time out or be truncated
- Sophisticated obfuscated injections may evade detection and pass through undetected
- Non-text binary content passed as the text field may produce unexpected results
- Payment failure (402) if x402 payment header is missing or USDC balance is 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://cve-intel.agentdiet.dev/v1/llm-guard)

## Output

Returns a structured object indicating whether the input contains prompt injection or jailbreak content, along with sanitized text with adversarial instructions removed or flagged, enabling safe downstream LLM consumption.

## 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/cve-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-ecd0430f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cve-intel.agentdiet.dev](https://www.zero.xyz/host/cve-intel.agentdiet.dev/llms.txt)