Security Risk Evaluation of ZombAI Claude: Prompt Injection as a Backdoor for Command and Control Exploits
The rapid adoption of AI in industrial automation has introduced AI agents functioning as Command and Control (C2) systems capable of managing infrastructure autonomously. The integration of "Computer Use" into Claude Sonnet 4.5 introduces critical vulnerabilities exploitable through prompt-injectio...
Uloženo v:
| Hlavní autoři: | , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
LPPM ISB Atma Luhur
2026-07-01
|
| Edice: | Jurnal Sisfokom |
| Témata: | |
| On-line přístup: | https://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/2634 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|