GuardBreaker: Derailing AI-assisted malware analysis with a code comment
ESET names 'GuardBreaker': UAC-0099 embeds a nuclear-weapon question in VBScript comments to trip LLM scanner guardrails during analysis of its MATCHBOIL loader.
ESET researchers observed the Russia-aligned group UAC-0099 inserting a decoy prompt injection into a VBScript used to install its MATCHBOIL loader in an attack against a Ukrainian target, aiming to make LLM-based code scanners refuse and stop inspecting the file. The comment triggers safety guardrails with a request about building a nuclear weapons but has no runtime effect. Similar LLM-thwarting tricks have appeared in malicious PyPI and npm packages reported by Socket and StepSecurity. ESET recommends multi-model cross-validation of AI-assisted analysis and treating missing LLM output as requiring further checks.
- GuardBreaker is prompt injection at inference time: untrusted file content triggers LLM refusal, halting analysis.
- The decoy comment asks about building nuclear weapons, invoking safety guardrails before malicious code is read.
- Similar LLM-thwarting tricks appeared in malicious PyPI and npm packages reported by Socket and StepSecurity.
- UAC-0099 also checked for analysis tools like IDA and Wireshark, showing awareness of AI-based defenses.
- ESET recommends multi-model cross-validation and treating absent LLM output as a trigger for further checks.
- Vendors
- ESETSocketStepSecurity
- Products
- GuardBreaker
- Threat actors
- UAC-0099
- Malware
- MATCHBOIL
- Countries
- Ukraine
From the original article
4 min read at welivesecurity.com
LLM-based code scanners won’t help attackers build a nuclear weapon, but that refusal could work in their favor
welivesecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.