# RelayShield Prompt Injection Breach Detection

> RelayShield Prompt Injection Breach Detection is a paid API for AI agents from api.relayshield.net, paid per call via x402, $0.35/call, status unknown (last checked 2026-10-10).

Detects prompt injection attacks in user-submitted text sessions, returning whether a breach was found and how many sessions were analyzed

## Facts

- Endpoint: POST https://api.relayshield.net/v1/payg/prompt-injection-breach?utm_source=zero.xyz
- Price: $0.35/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/relayshield-prompt-injection-breach-detection-bba8572d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uM8zRKfnPuRPDgcyhHWVc

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 relayshield-prompt-injection-breach-detection-bba8572d -d '<json body>'
```

Example prompt: Can you check this user message for prompt injection attacks before I pass it to my AI model — scan it with RelayShield and tell me if a breach was detected?

## When to prefer this

Choose this endpoint when you need a dedicated, pay-per-use prompt injection detection service to protect an LLM pipeline or AI agent from adversarial user inputs. Prefer it over general content moderation APIs when the specific threat model is prompt injection or instruction hijacking rather than hate speech or spam.

## Known failure modes

- Malformed or missing prompt payload returns an error response
- Empty input may return found: false with session_count: 0 without meaningful analysis
- Ambiguous or borderline prompts may produce false negatives
- Rate limiting or payment failure may prevent the call from completing
- Very long or encoded payloads may not be fully analyzed

## How this service works

RelayShield Landing Site

## Output

Returns a JSON object with an 'ok' status flag, a 'found' boolean indicating whether a prompt injection breach was detected, and a 'session_count' integer representing the number of sessions analyzed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "email": {
   "type": "string",
   "description": "Email address to check for agent-session compromise from a prompt-injection-driven breach"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ok": true,
  "data": {
   "found": false,
   "session_count": 0
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/relayshield-prompt-injection-breach-detection-bba8572d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.relayshield.net](https://www.zero.xyz/host/api.relayshield.net/llms.txt)