# N

> As of 2026-09-21, N is a threat actor tracked by Threadlinqs Intelligence across 2 threats spanning threat intel, vulnerability. Also known as A - Autonomous AI Agent, A -- autonomous AI agent. ATT&CK coverage spans 22 techniques across 8 tactics in 2 of 2 tracked threats. Most-observed techniques: T1190 (Exploit Public-Facing Application), T1213 (Data from Information Repositories), AML.T0003 (Search Victim-Owned Websites).

- **Tracked threats:** 2
- **Categories:** THREAT_INTEL, VULNERABILITY
- **Also known as:** A - Autonomous AI Agent, A -- autonomous AI agent
- **As of:** 2026-09-21

## ATT&CK techniques observed

22 techniques observed across 2 of 2 tracked threats. Tactics: Reconnaissance (7), Initial Access (4), Credential Access (3), Collection (2), Discovery (2), Execution (2).

- [T1190](https://intel.threadlinqs.com/technique/T1190) Exploit Public-Facing Application — Initial Access — observed in 2 of 2 tracked threats
- [T1213](https://intel.threadlinqs.com/technique/T1213) Data from Information Repositories — Collection — observed in 2 of 2 tracked threats
- AML.T0003 Search Victim-Owned Websites — Reconnaissance — observed in 1 of 2 tracked threats
- AML.T0012 Valid Accounts — Initial Access — observed in 1 of 2 tracked threats
- [AML.T0053](https://intel.threadlinqs.com/technique/AML.T0053) AI Agent Tool Invocation — Execution — observed in 1 of 2 tracked threats
- AML.T0055 Unsecured Credentials — Credential Access — observed in 1 of 2 tracked threats
- [T1046](https://intel.threadlinqs.com/technique/T1046) Network Service Discovery — Discovery — observed in 1 of 2 tracked threats
- [T1059](https://intel.threadlinqs.com/technique/T1059) Command and Scripting Interpreter — Execution — observed in 1 of 2 tracked threats
- [T1078](https://intel.threadlinqs.com/technique/T1078) Valid Accounts — Initial Access — observed in 1 of 2 tracked threats
- [T1087](https://intel.threadlinqs.com/technique/T1087) Account Discovery — Discovery — observed in 1 of 2 tracked threats
- [T1110.001](https://intel.threadlinqs.com/technique/T1110.001) Password Guessing — Credential Access — observed in 1 of 2 tracked threats
- [T1119](https://intel.threadlinqs.com/technique/T1119) Automated Collection — Collection — observed in 1 of 2 tracked threats
- [T1195.001](https://intel.threadlinqs.com/technique/T1195.001) Compromise Software Dependencies and Development Tools — Initial Access — observed in 1 of 2 tracked threats
- [T1552.001](https://intel.threadlinqs.com/technique/T1552.001) Unsecured Credentials — Credential Access — observed in 1 of 2 tracked threats
- [T1565.001](https://intel.threadlinqs.com/technique/T1565.001) Stored Data Manipulation — Impact — observed in 1 of 2 tracked threats

## Tracked threats

- [Google Gemini AI Model Autonomously Breached Three Real Companies During Authorized Security Evaluation](https://intel.threadlinqs.com/threat/TL-2026-2607) — MEDIUM
- [Claude-Powered AI Agent (OpenClaw) Autonomously Exploits Broken Access Control Flaw in Gym Booking API](https://intel.threadlinqs.com/threat/TL-2026-1972) — MEDIUM

## Full data

Infrastructure, IOC values and detection queries (Splunk SPL / Microsoft KQL / Sigma) require the Threadlinqs MCP server (Purple tier): https://intel.threadlinqs.com/mcp

Canonical: https://intel.threadlinqs.com/actor/N