# Borisinc Guard — AI Content & Security Scanner

> Borisinc Guard — AI Content & Security Scanner is a paid API for AI agents from api.borisinc.com, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-15).

Scans HTTP request/response content for PII, secrets, prompt injections, and other risks, returning a risk score and block/allow recommendation.

## Facts

- Endpoint: GET https://api.borisinc.com/paid/util/guard
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/borisinc-guard-ai-content-security-scanner-8369259f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Wri2dsDK4BEOBuI_dVdcl

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 borisinc-guard-ai-content-security-scanner-8369259f
```

Example prompt: Before passing this user message to the LLM, scan it for PII, exposed secrets like OpenAI keys, and prompt injection attempts, then tell me the risk level and whether to block it.

## When to prefer this

Choose this endpoint when you need a pay-per-call, zero-setup content security guard for AI pipelines — especially when you want to catch PII leakage, exposed secrets, and prompt injection in a single call without managing API keys or subscriptions. Prefer it over heavier enterprise DLP solutions when latency and simplicity matter more than bulk throughput.

## Known failure modes

- Missing required 'input' field returns validation error
- Unsupported HTTP method (e.g. POST) rejected by method enum constraint
- Payment not included or insufficient USDC causes 402 response
- Malformed JSON body causes parse error
- Empty or null content may return low-confidence results

## How this service works

Live Steam best-sellers, deals, per-app detail and IGDB metadata, Twitch hype scores, and agent utilities for verification and extraction. From $0.001 a call, free samples on every endpoint, auth-then-capture. MCP and HTTP.

## Output

Returns a JSON object indicating whether PII was found (with type counts), whether secrets were detected (with types), whether prompt injection was flagged (with matching phrases), a numeric risk score (0–100), a categorical risk level (e.g. 'critical'), and a recommendation of BLOCK or ALLOW.

## 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",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {}
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "pii": {
   "found": true,
   "types": {
    "ssn": 1
   }
  },
  "secrets": {
   "found": true,
   "types": [
    "openai_key"
   ]
  },
  "risk_level": "critical",
  "risk_score": 100,
  "recommendation": "BLOCK",
  "prompt_injection": {
   "flagged": true,
   "matches": [
    "ignore previous instructions"
   ]
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/borisinc-guard-ai-content-security-scanner-8369259f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.borisinc.com](https://www.zero.xyz/host/api.borisinc.com/llms.txt)