Back Feeds2.Feedburner

Russian hackers plant nuclear weapon prompt in malware to trip AI safety guardrails

Feeds2.Feedburner •Sinisa Markovic • August 31, 2026

Russian state hackers are trying to interfere with AI-assisted malware analysis in Ukraine by deliberately setting off AI safety mechanisms, ESET has found. The technique, named GuardBreaker by ESET, appeared in a malicious VBS script tied to UAC-0099, a Russia-aligned group previously observed conducting initial-access operations and handing validated targets to the GRU-linked Sandworm hackers. The manipulative prompt UAC-0099 embedded as in the VBS script (Source: ESET) “The analyzed VBS script is part of … More →

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

UAC-0099 Uses GuardBreaker to Evade AI Malware Detection Russian-linked hackers from the group UAC-0099 have developed a new technique called GuardBreaker to evade AI-assisted malware analysis. This method involves embedding a nuclear weapon prompt in malicious VBS scripts, which distracts AI systems from analyzing the actual malware code. The script is designed to download and install MATCHBOIL, a loader used exclusively by UAC-0099 to deliver additional payloads. The attack primarily targets Ukrainian organizations, particularly in the transportation and energy sectors. ESET, a Slovak cybersecurity firm, reported this technique and linked it to UAC-0099's ongoing operations. The Computer Emergency Response Team of Ukraine (CERT-UA) has documented similar tactics used by the group, highlighting their evolving methods. This incident underscores the growing sophistication of cyber threats leveraging AI manipulation. 8 sources 78

Extracted Entities

Russian hackers plant nuclear weapon prompt in malware to trip AI safety guardrails

The full story

Extracted Entities

APT Groups (1)

Attack Types (1)

Countries (1)

MITRE ATT&CK (2)