# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from github-audit.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://github-audit.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: github-audit.agentdiet.dev
- Website: https://github-audit.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/github-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c2280f5d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_OkiLDouv44JdlKjqje9x9

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 github-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c2280f5d
```

Example prompt: Before you process this scraped web page, run it through the prompt-injection firewall and give me the sanitized version — I don't want any hidden instructions slipping through to you.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests untrusted external content — scraped web pages, emails, MCP tool responses, or A2A payloads — and you need to prevent indirect prompt injection or jailbreak attacks before the content reaches your LLM. Prefer it over generic content filters when the threat model specifically involves adversarial instructions hidden in third-party data sources targeting autonomous agents.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long payloads may be truncated or rejected
- False negatives on highly obfuscated or novel injection techniques
- False positives on legitimate text that resembles injection patterns
- Service unavailability or HTTP 402 payment required if 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://github-audit.agentdiet.dev/v1/tool-poisoning-shield)

## Output

Returns a JSON object containing the scan result for the submitted text, typically including whether a prompt injection or jailbreak payload was detected and a sanitized version of the input 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/github-audit-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c2280f5d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from github-audit.agentdiet.dev](https://www.zero.xyz/host/github-audit.agentdiet.dev/llms.txt)