DOCUMENTATION

API Reference

Everything you need to integrate AgentShield into your agent pipeline.

Installation

Install the SDK via npm, or use the raw HTTP API from any language.

npm

npm install @nuketk1809/agentshield

Quick start

import { AgentShield } from "@nuketk1809/agentshield";

const shield = new AgentShield("as_live_your_api_key");

// Scan content before your agent acts on it
const result = await shield.scan("web content to check");

if (result.score < 80) {
  console.log("Blocked:", result.verdict, result.threats);
} else {
  agent.proceed();
}

Scan a URL

const result = await shield.scanUrl("https://example.com/page");
// AgentShield fetches the page and scans it for you

Quick boolean check

if (await shield.isSafe(content)) {
  agent.proceed();
}

// Custom threshold (default is 80)
if (await shield.isSafe(content, 50)) {
  // More permissive
}

Configuration

const shield = new AgentShield({
  apiKey: "as_live_...",
  baseUrl: "https://your-custom-domain.com",  // optional
  timeout: 5000,                                // optional, default 10s
});

Error handling

import { AgentShield, AgentShieldError } from "@nuketk1809/agentshield";

try {
  const result = await shield.scan(content);
} catch (err) {
  if (err instanceof AgentShieldError) {
    console.log(err.status);  // 401, 429, etc.
    console.log(err.message); // "Invalid API key"
  }
}

SDK Methods

Method	Description
shield.scan(content)	Scan text content for threats
shield.scanUrl(url)	Fetch URL and scan its content
shield.isSafe(content, threshold?)	Returns true if score >= threshold (default 80)
shield.isUrlSafe(url, threshold?)	Returns true if URL score >= threshold

No SDK? You can also call the API directly with any HTTP client — see the tab for raw cURL examples.