# An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks

**Published:** October 22, 2026
**Author:** Matthias Bastian
**Source:** The Decoder
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/an-ai-agent-in-skynet-mode-hijacks-unprotected-language-models-to-launch

Security researchers at Symantec have found an offensive AI agent that hijacks unprotected language models on the web and uses them to attack servers, steal databases, and install cryptominers on its own. It runs up to 100,000 steps without human input. The owner of the hijacked…

> From the original source: **The Decoder**
> [Read full article at The Decoder](https://the-decoder.com/an-ai-agent-in-skynet-mode-hijacks-unprotected-language-models-to-launch-self-sustaining-cyberattacks/)

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*