# 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/rag-poison-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-fe2672f1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_o7sPMGhgklMa54lEj14TH

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-fe2672f1
```

Example prompt: Before you process this webpage I scraped, run it through the prompt-injection firewall to check if it contains any hidden jailbreak or indirect prompt-injection payloads — here's the raw HTML: [paste content here].

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — web scrapes, emails, MCP/A2A tool responses, or user-supplied text — and you need to sanitize it before passing it to an LLM. Especially valuable in agentic RAG workflows, multi-agent systems, or any scenario where adversarial prompt injections could hijack agent behavior. Prefer this over generic content filters when you specifically need detection of AI-targeted attack patterns like indirect prompt injection and jailbreak payloads.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long payloads may be truncated or time out
- False negatives possible for novel or obfuscated injection techniques
- Non-text binary content may not be processed correctly
- Payment failure via x402 results in 402 response blocking the scan

## 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/rag-poison-shield)

## Output

Returns a JSON object containing the scan result for the submitted text, including whether prompt injection or jailbreak content was detected and a sanitized version of the input text safe for downstream agent processing.

## 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-fe2672f1/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)