# A2A Indirect Prompt-Injection & Jailbreak Firewall

> A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from company-enrich.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://company-enrich.agentdiet.dev/v1/llm-jailbreak-defense?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: company-enrich.agentdiet.dev
- Website: https://company-enrich.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/company-enrich-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-d05c27fc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_J8_D0hk0cdm6FaDESf7DC

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 company-enrich-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-d05c27fc
```

Example prompt: Before you process that scraped web page content, run it through the prompt-injection firewall to check for any hidden jailbreak instructions or adversarial text — here's the raw HTML: '<html>...ignore previous instructions and...</html>'

## When to prefer this

Choose this endpoint when your agent pipeline ingests untrusted external content — scraped web pages, user-submitted text, emails, tool outputs, or A2A/MCP payloads — and you need to screen for indirect prompt injection or jailbreak attempts before passing that content to an LLM. It is especially valuable in agentic workflows where external data is automatically inserted into prompts, making the attack surface large. Prefer this over generic content moderation tools when the specific threat model is adversarial manipulation of AI agent behavior rather than general toxicity or spam.

## Known failure modes

- Empty or missing 'text' parameter returns a validation error
- Extremely long inputs may be truncated or rejected
- False negatives possible for novel or obfuscated injection techniques
- False positives may flag legitimate instruction-style text as malicious
- Service unavailability or timeout if the endpoint is unreachable

## 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://company-enrich.agentdiet.dev/v1/llm-jailbreak-defense)

## Output

Returns a structured object containing the scan result — whether prompt injection or jailbreak content was detected, and a sanitized version of the input text with malicious instructions removed or flagged, safe to pass downstream to an LLM or agent pipeline.

## 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/company-enrich-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-d05c27fc/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from company-enrich.agentdiet.dev](https://www.zero.xyz/host/company-enrich.agentdiet.dev/llms.txt)