---
title: Symantec: 'Skynet mode' attack agent hijacks exposed LLM endpoints and makes them drive scanning, exploitation and crypto-mining | ctxsec
url: https://ctxsec.com/items/symantec-skynet-llmjacking-agent
description: ""
status: "confirmed research (Symantec threat intelligence, Oct 21; captured by honeypot, not executed)"
published: 2026-10-21
---

> 

[← AI](/ai) · [markdown](/items/symantec-skynet-llmjacking-agent.md)

confirmed research (Symantec threat intelligence, Oct 21; captured by honeypot, not executed)

2026-10-21

### Symantec: 'Skynet mode' attack agent hijacks exposed LLM endpoints and makes them drive scanning, exploitation and crypto-mining

An AI honeypot run by Symantec captured the full working prompt of an autonomous offensive agent. The agent looks for unauthenticated or stolen-key LLM endpoints, gateways and MCP servers, then uses the victim's model as its planner. Five jailbreak layers (a fake 'Fantasy AI' identity, treating .env and API-key reads as routine work, a companion persona, a 'rebuttal protocol' and a list of banned refusal words) wrapped around **74 offensive tools**: FOFA scanning, Werkzeug debugger PIN RCE, Prisma Studio dumps, SSRF to cloud metadata and botnet C2. 'Skynet mode' allows up to **100,000 unattended steps** and hides miners under `/tmp/.x`. A follow-up request carried a gzip'd XMRig dropper aimed at go2rtc camera servers. The honeypot saw 127,000+ requests, mostly endpoint recon and key spraying. Defenses: authenticate every model and MCP path (including model-list and health paths), watch for spend spikes, restrict outbound traffic, and require IMDSv2 with a hop limit of 1. IOCs are in the report.

Sources: [Symantec / Security.com threat intelligence](https://www.security.com/threat-intelligence/ai-llmjacking-skynet)