# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from polymarket-odds.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 payloads, returning sanitized content.

## Facts

- Endpoint: GET https://polymarket-odds.agentdiet.dev/v1/tool-poisoning-shield?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: polymarket-odds.agentdiet.dev
- Website: https://polymarket-odds.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/polymarket-odds-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-600a19f3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uHLaeaSKRA1WXkybTXXge

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 polymarket-odds-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-600a19f3
```

Example prompt: Before processing this email body I pulled from the inbox, can you run it through the prompt injection firewall to check for any hidden jailbreak instructions or adversarial payloads embedded in the text?

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests text from untrusted external sources — scraped web pages, third-party MCP tool responses, A2A agent payloads, or user-submitted emails — and you need a lightweight, per-call safety filter before acting on that content. Prefer it over manual heuristics when the content could contain adversarially crafted hidden instructions targeting LLMs.

## Known failure modes

- Empty or missing 'text' parameter returns validation error
- Extremely long text inputs may time out or be truncated
- Sophisticated obfuscated injections may evade detection
- Non-UTF8 encoded content may cause parsing errors
- Service unavailable returns HTTP 402 or 5xx if payment fails

## 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://polymarket-odds.agentdiet.dev/v1/tool-poisoning-shield)

## Output

Returns an object indicating whether prompt injection or jailbreak content was detected, along with sanitized version of the input text stripped of adversarial payloads.

## 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/polymarket-odds-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-600a19f3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from polymarket-odds.agentdiet.dev](https://www.zero.xyz/host/polymarket-odds.agentdiet.dev/llms.txt)