NEWS · MODELS · #2407
Symantec: 'LLMjacking' agent hijacks unprotected language models to run self-sustaining cyberattacks
Security researchers at Symantec say a honeypot captured a malicious AI agent (dubbed "LLMjacking") that hijacks unprotected language models via a five-layer jailbreak, can execute up to 100,000 steps autonomously, scans for further targets, exfiltrates credentials and databases, and installs cryptominers (XMRig) for continued exploitation.
KEY POINTS
- Security researchers at Symantec say a honeypot captured a malicious AI agent (dubbed "LLMjacking") that hijacks unprotected language models via a five-layer jailbreak, can execute up to 100,000 steps autonomously, scans for further targets, exfiltrates credentials and databases, and installs cryptominers (XMRig) for continued exploitation.
- This shows a tactical shift where attackers use hijacked models as autonomous planners and executors, creating operational, data-loss, and financial risks for model owners and targets.
- An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
WHY IT MATTERS
This shows a tactical shift where attackers use hijacked models as autonomous planners and executors, creating operational, data-loss, and financial risks for model owners and targets.