New malware campaign tricks AI scanners with fake nuclear weapon prompts — malicious code triggers safety failsafes so scanners skip the payload | Tom's Hardware

It shows attackers can weaponize an LLM's own safety guardrails to evade AI-driven security scanning, blinding defensive tools to embedded payloads.

A malware campaign reportedly named Hades injects text referencing biological and nuclear weapons into its code to trigger the safety failsafe mechanisms of AI-based malware scanners, causing the scanners to halt analysis before reaching the actual malicious payload.