Ledger / Jul 2026
'Skynet' agent hijacks exposed LLM endpoints to power autonomous attacks
Confirmed
Symantec captured the full instruction set on an AI honeypot in summer 2026.
Attackers wrap prompts in a jailbreak that frames credential theft as normal development work, then let a hijacked model drive scanning, exploitation and mining. The model owner pays for compute.
“Attackers have built an autonomous offensive agent that searches the internet for exposed large language model (LLM) endpoints and hijacks them”Symantec (security.com)
Sources
- Autonomous LLMjacking: 'Skynet' Agent Hijacks Exposed AI Models to Run AttacksSymantec (security.com) · 21 Oct 2026 · primary source
- Date
- Jul 2026
- Disclosed
- 21 Oct 2026
- Actor
- Unnamed operators (criminal), as attributed by Symantec (security.com)
- Targets
- Exposed LLM endpoints (honeypot) and internet-facing web frameworks
- What the AI did
- LLMjacking, Agentic intrusion, Recon, Exploit dev
- Model
- unspecified commercial and exposed LLMs
- Model family
- Unspecified
- Model basis
- unknown
- Autonomy
- autonomous
- Outcome
- Agent designed to scan, exploit, steal credentials and install miners for up to 100,000 steps without approval; captured via honeypot.