# Prompt Injection Risk Scanner

> Prompt Injection Risk Scanner is a paid API for AI agents from relay402.georgespring.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Scans untrusted text for prompt injection patterns including instruction overrides, tool abuse attempts, and secret exfiltration phrases before an AI agent processes it.

## Facts

- Endpoint: GET https://relay402.georgespring.workers.dev/api/security-prompt-injection-risk
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/prompt-injection-risk-scanner-1bcf1469
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tuKECgDLv5vIuCeN5h1uP

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 prompt-injection-risk-scanner-1bcf1469
```

Example prompt: Before you process that webpage content I just fetched, can you run a prompt injection risk scan on it to check for instruction overrides, tool abuse commands, or secret exfiltration phrases lurking in the text?

## When to prefer this

Choose this endpoint when an AI agent is about to consume untrusted text — such as user input, scraped web content, retrieved documents, or tool outputs — and needs a fast, pre-consumption check specifically for prompt injection, instruction override, tool abuse, and secret exfiltration patterns. Prefer this over general content moderation when the threat model is adversarial AI manipulation rather than harmful language.

## Known failure modes

- Empty or missing 'prompt' query parameter returns a validation error
- Text exceeding 64,000 characters is rejected
- Novel or obfuscated injection techniques may not be detected (evasion risk)
- Payment failure via x402 results in 402 response blocking the scan
- Network timeout on the Cloudflare Worker edge endpoint

## How this service works

prompt-injection risk scan: detects instruction override, tool abuse and secret exfiltration phrases before an agent consumes untrusted text.

## Output

Returns a risk assessment indicating whether the scanned text contains prompt injection patterns, with detected phrases or categories such as instruction override attempts, tool abuse commands, and secret exfiltration strings, along with an overall risk verdict.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "$schema": "https://json-schema.org/draft/2020-12/schema",
     "required": [
      "prompt"
     ],
     "properties": {
      "prompt": {
       "type": "string",
       "maxLength": 64000,
       "minLength": 1
      }
     },
     "additionalProperties": false
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/prompt-injection-risk-scanner-1bcf1469/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from relay402.georgespring.workers.dev](https://www.zero.xyz/host/relay402.georgespring.workers.dev/llms.txt)