Symantec Captures a Skynet Mode AI Attack Agent Built to Hijack Exposed Models for 100,000 Unattended Steps
Posted on 25th Oct 2026 11:03:09 in Artificial Intelligence, Machine Learning
Tagged as: AI security, LLMjacking, Symantec, autonomous agents, cybercrime, MCP servers
Symantec's Threat Hunter Team caught a fully autonomous offensive AI agent in a honeypot. Its 'Skynet mode' hijacked exposed LLM endpoints to scan, exploit and mine crypto for 100,000 steps.
