AI Malware Keeps Changing Its Code to Break Traditional Signature-Based Detection
Google's GTIG documents AI-enabled malware PROMPTFLUX and PROMPTSTEAL that query LLMs at runtime to rewrite code and evade signature-based detection.
Google Threat Intelligence Group documented 'just-in-time' AI-enabled malware that queries language models during execution. PROMPTFLUX, an experimental VBScript dropper, calls the Gemini API to regenerate and obfuscate its own source code and writes variants to the Windows Startup folder for persistence. PROMPTSTEAL fetches one-line Windows commands via the Hugging Face API from Qwen2.5-Coder-32B-Instruct to collect files and system information, which Google linked to APT28 activity targeting Ukraine. The article argues signature-based defenses retain value but defenders should prioritize behavioral detection and deterministic prevention controls.
- PROMPTFLUX is a VBScript dropper that calls the Gemini API to regenerate obfuscated code
- PROMPTSTEAL obtains one-line Windows commands from Qwen2.5-Coder-32B-Instruct via Hugging Face API
- PROMPTFLUX writes regenerated code to the Windows Startup folder, coupling evasion with persistence
- Google linked PROMPTSTEAL's live LLM use to APT28 activity targeting Ukraine
- Defenders advised to favor behavioral detection and prevention over hash or signature matching
- ATT&CK
- T1027 Obfuscated Files or InformationT1547.001 Registry Run Keys & Startup FolderT1059.003 Windows Command ShellT1082 System Information DiscoveryT1005 Data from Local System
- Products
- GeminiQwen2.5-Coder-32B-Instruct
- Threat actors
- APT28
- Malware
- PROMPTFLUXPROMPTSTEAL
- Organizations
- Google Threat Intelligence Group
- AI models
- GeminiQwen2.5-Coder-32B-Instruct
From the original article
4 min read at gbhackers.com
AI-powered malware is beginning to erode one of endpoint security’s oldest assumptions: that malicious code will remain stable long enough to identify, fingerprint, and block. A new class of threats uses large language models during execution to rewrite scripts, generate commands, and alter obfuscation on demand producing variants that can evade static hashes and traditional […]
By Mayura Kathir · gbhackers.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.