# AI Security Guard Preflight Check

> AI Security Guard Preflight Check is a paid API for AI agents from aisecurityguard.io, paid per call via x402, $0.0075/call, status unknown (last checked 2026-09-14).

Validates an AI request (URL, tool call, or document) for security threats, policy violations, and data exfiltration risks before execution.

## Facts

- Endpoint: POST https://aisecurityguard.io/v1/guard/preflight
- Price: $0.0075/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/aisecurityguard-io-ad9a565b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eEzP8ZA9s9W8QZppJxTMr

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 aisecurityguard-io-ad9a565b -d '<json body>'
```

Example prompt: Before my AI agent fetches this URL, run a preflight security check on it to detect any sensitive parameter names or exfiltration risks: https://api.example.com/data?token=abc123

## When to prefer this

Use this endpoint when an AI agent is about to execute an untrusted or externally-sourced action — particularly fetching a URL, calling an MCP tool, or processing a document — and you need a fast, paid security verdict before proceeding. Prefer this over manual inspection when automated, low-latency preflight validation with confidence scoring is required in an agentic pipeline.

## Known failure modes

- Invalid request type enum — must be 'url', 'tool', or 'document'
- Malformed or missing 'value' field returns a 400 error
- Payment not attached or insufficient USDC balance triggers x402 payment required response
- Unreachable or invalid URL format may return low-confidence result
- Service downtime returns 503 — preflight cannot be completed

## How this service works

Knowledge, understanding, and tooling is power. Research-backed education on agentic security, free resources, then AgentGuard360 and Protection SDK when you're ready to protect what you ship.

## Output

Returns a verdict ('suspicious' or safe), a confidence score (0–1), a list of security flags (e.g. 'sensitive_param_name:token'), an exfiltration risk description, domain and scheme details, and a boolean 'valid' and 'suspicious' field — giving the agent a clear go/no-go signal before executing the request.

## Example request

```json
{
 "type": "url",
 "value": "https://api.example.com/user/profile?session_id=abc123def456"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "type": {
   "enum": [
    "url",
    "price",
    "integer",
    "address",
    "hash"
   ],
   "type": "string",
   "description": "Validation type to perform."
  },
  "chain": {
   "type": "string",
   "description": "Blockchain for address validation: evm, solana (default: evm)."
  },
  "value": {
   "type": "string",
   "description": "The value to validate."
  },
  "decimals": {
   "type": "integer",
   "description": "Token decimals for price validation (default: 18)."
  },
  "int_type": {
   "type": "string",
   "description": "Integer bounds: uint8, uint256, int128, etc. (default: uint256)."
  },
  "hash_type": {
   "type": "string",
   "description": "Hash type: sha256, keccak256, tx_hash, md5 (default: sha256)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "result": {
   "type": "url",
   "flags": [
    "javascript_in_param",
    "suspicious_tld"
   ],
   "valid": true,
   "value": "https://api.malicious-site.com/redirect?to=javascript:alert(1)",
   "details": {
    "domain": "malicious-site.com",
    "scheme": "https"
   },
   "verdict": "suspicious",
   "confidence": 0.88,
   "suspicious": true
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/aisecurityguard-io-ad9a565b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from aisecurityguard.io](https://www.zero.xyz/host/aisecurityguard.io/llms.txt)