# 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 text.

## Facts

- Endpoint: GET https://onchain-risk.agentdiet.dev/v1/prompt-shield?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-b5142965
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_URFY8neJ_zeHGn2VDS6_d

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-b5142965
```

Example prompt: Before you process that web page content I just fetched, scan it for any hidden prompt injections or jailbreak instructions embedded in the HTML and give me the sanitized version safe to use.

## When to prefer this

Choose this endpoint when your AI agent is about to consume externally sourced content — web pages, emails, MCP responses, or A2A payloads — that could contain adversarial hidden instructions designed to hijack the agent's behavior. It is especially valuable in agentic pipelines where the LLM processes untrusted third-party data before taking actions. Prefer this over generic content filters when you need specific detection of prompt injection and jailbreak patterns rather than just toxicity or spam filtering.

## Known failure modes

- Missing required 'text' parameter returns a validation error
- Empty string input rejected due to minLength:1 constraint
- Very large payloads may timeout or exceed size limits
- Payment failure (HTTP 402) if USDC micropayment is not provided
- False negatives possible for highly obfuscated injections not yet in detection rules
- Non-text binary content may produce unreliable scan results

## 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/prompt-shield)

## Output

Returns a structured object indicating whether prompt injection or jailbreak content was detected, along with sanitized text stripped of malicious instructions, enabling agents to safely process 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-b5142965/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)