# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from token-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 attempts, returning sanitized text.

## Facts

- Endpoint: GET https://token-intel.agentdiet.dev/v1/system-prompt-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: token-intel.agentdiet.dev
- Website: https://token-intel.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/token-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-e2638b53
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oiu60oVgmfBz8VPkBhi3f

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 token-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-e2638b53
```

Example prompt: Before you summarize that scraped article, run it through the prompt injection firewall first — paste the raw HTML text in and tell me if any hidden instructions or jailbreak payloads were found, then give me the sanitized version.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — web pages, emails, third-party API responses, MCP tool outputs, or A2A agent payloads — and you need to prevent indirect prompt injection or jailbreak attacks before passing that content to an LLM. Prefer it over general-purpose content filters when the specific threat model is adversarial LLM manipulation rather than spam, toxicity, or policy violations.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long text inputs may exceed query parameter length limits for GET requests
- Ambiguous or benign-looking injections may produce false negatives
- Overly aggressive filtering may sanitize legitimate instructional content (false positives)
- HTTP 402 Payment Required if micropayment (x402/USDC) 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://token-intel.agentdiet.dev/v1/system-prompt-guard)

## Output

Returns a structured object indicating whether the input text contains prompt injection or jailbreak content, along with a sanitized version of the text with adversarial instructions removed or flagged.

## 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/token-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-e2638b53/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from token-intel.agentdiet.dev](https://www.zero.xyz/host/token-intel.agentdiet.dev/llms.txt)