# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from onchain-risk.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 injections and jailbreak attempts, returning sanitized output.

## Facts

- Endpoint: GET https://onchain-risk.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: onchain-risk.agentdiet.dev
- Website: https://onchain-risk.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-151506df
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_65aDN0aD8EuLzRfpucUSu

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 onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-151506df
```

Example prompt: Before you summarize that webpage I just scraped, scan the raw HTML for hidden prompt injections or jailbreak payloads and give me the sanitized version — I don't want any adversarial instructions sneaking into your context.

## When to prefer this

Choose this endpoint when your AI agent consumes content from untrusted external sources — web scraping, email ingestion, third-party MCP/A2A tool responses, or user-submitted data — and you need a dedicated firewall layer to catch indirect prompt injections before they corrupt your agent's behavior. Particularly valuable in multi-agent pipelines where one compromised upstream payload could cascade through the entire system.

## Known failure modes

- Empty or missing 'text' parameter returns a 400 validation error
- Very large payloads may exceed size limits or timeout
- False negatives possible for novel obfuscated injection techniques not yet in detection patterns
- Non-text binary content may not be parsed correctly
- Payment failure (HTTP 402) if x402 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://onchain-risk.agentdiet.dev/v1/system-prompt-guard)

## Output

Returns a structured object indicating whether prompt injection or jailbreak content was detected in the input text, along with a sanitized version of the text with malicious instructions removed or flagged, so the agent can safely use the cleaned output.

## 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/onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-151506df/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from onchain-risk.agentdiet.dev](https://www.zero.xyz/host/onchain-risk.agentdiet.dev/llms.txt)