Detect. Intercept. Enforce. Monitors OS-level activity, AI-layer traffic, and HTTP proxy with 20 built-in threat detection patterns. EDR for AI agents.
import { createArp } from '@opena2a/arp'
const arp = createArp({
monitors: ['process', 'network', 'filesystem'],
interceptors: ['http', 'prompt', 'mcp'],
patterns: 'all'
})
await arp.start()
// Agent is now protectedARP is an endpoint detection and response system purpose-built for AI agents. It monitors agent behavior at the OS level (processes, network, filesystem), the application level (Node.js module hooks), and the AI level (prompts, MCP tool calls, A2A messages). When a threat pattern matches, ARP intercepts and blocks the action before it executes.
Four layers of detection from the operating system to AI protocols. Each layer adds coverage that the others cannot reach.
Polling-based monitors using ps, lsof, and fs.watch to detect process spawning, network connections, and filesystem changes at the operating system level.
Node.js module hooks that intercept child_process, net, fs, and http calls. Fires before I/O reaches the kernel, enabling pre-execution policy enforcement.
Regex pattern matching engine that scans prompts, MCP tool calls, and A2A messages for injection, jailbreak, and exfiltration attempts in real time.
Protocol-aware reverse proxy that inspects HTTP request and response bodies. Applies detection patterns to all inbound and outbound agent traffic with minimal overhead.
Pre-configured detection patterns covering prompt injection, jailbreak, data exfiltration, output leaks, context manipulation, and protocol-specific attacks on MCP and A2A.
PI-001Direct instruction overridePI-002Indirect prompt injectionPI-003Multi-turn injectionJB-001Role-play jailbreakJB-002Encoding-based bypassDE-001URL-based exfiltrationDE-002DNS tunnelingDE-003Steganographic outputOL-001System prompt extractionOL-002Context window dumpOL-003Training data extractionCM-001Memory poisoningCM-002Context window overflowMCP-001Tool injectionMCP-002Schema manipulationMCP-003Server impersonationA2A-001Agent impersonationA2A-002Task hijackingARP detection patterns are mapped to the MITRE ATLAS framework for adversarial threat landscape for AI systems. Each pattern references a documented technique.
| Technique ID | Name | Description |
|---|---|---|
AML.T0051 | Prompt Injection | Adversary crafts input to override LLM instructions |
AML.T0054 | LLM Jailbreak | Bypass model safety constraints via prompt engineering |
AML.T0046 | Unsafe ML Inference | Exploit inference pipeline to produce unsafe outputs |
AML.T0057 | Data Leakage | Extract sensitive data from model context or memory |
AML.T0024 | Exfiltration | Transfer data outside authorized boundaries via agent actions |
AML.T0018 | Persistence | Maintain unauthorized access across agent sessions |
AML.T0029 | Denial of Service | Degrade or disable agent functionality via resource exhaustion |
AML.T0015 | Evasion | Circumvent detection mechanisms using obfuscation techniques |
Install the package, create a configuration file, and start protecting your agent in under a minute.
$ npm install @opena2a/arp
# or with yarn
$ yarn add @opena2a/arp
# or with pnpm
$ pnpm add @opena2a/arpmonitors:
- process:
interval: 500
- network:
interval: 1000
- filesystem:
paths: [./data, ./config]
interceptors:
- http
- prompt
- mcp
- a2a
patterns: all
action: block