cd /news/ai-safety/citrus-ransomware-uses-llm-generated… · home › topics › ai-safety › article
[ARTICLE · art-172051] src=securelist.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Citrus ransomware uses LLM-generated scripts in Windows attacks

Kaspersky documented a previously unreported Russian-speaking group it calls Citrus that breaches Russian companies using credentials stolen from contractors and relies on large language models for parts of its Windows work, including PowerShell and batch scripts carrying explanatory comments in a style Kaspersky associates with model output. The operators used Impacket's atexec for scheduled tasks and attempted CVE-2026-54121, an authentication bypass Kaspersky calls Certighost, which left machine accounts named GHOST followed by random letters and used an attacker-controlled endpoint at 91.210.109.118; one PowerShell payload included an exploit for CVE-2020-1337, the same code available in Metasploit. For impact, Citrus disguised a Group Policy deployment as Kaspersky software, disabled Defender through the registry and encrypted systems with a Sn00py-family trojan, and Kaspersky noted shared tools and, in some incidents, shared compromised infrastructure with Toy Ghouls, another Russian-speaking group targeting Russian companies.

recommendation

Hunt for LLM-style commented PowerShell and batch scripts, GHOST-prefixed machine accounts and traffic to 91.210.109.118, and block Impacket atexec and the Certighost CVE-2026-54121 bypass path.

more in playbook: Securing agents and AI tools
read1 min views17 publishedNov 11, 2026

Kaspersky documented a previously unreported Russian-speaking group it calls Citrus, which enters Russian companies through credentials stolen from contractors and then leans on large language models for parts of the Windows work. The group ran PowerShell and batch files, and also commands and full scripts that carried explanatory comments in a style Kaspersky associates with model output, including a script that enumerated logged-on users across domain systems with a thread limit. The operators used Impacket's atexec for scheduled tasks and tried CVE-2026-54121, an authentication bypass Kaspersky calls Certighost, which left machine accounts named GHOST followed by random letters and used an attacker-controlled endpoint at 91.210.109.118. In one case a PowerShell payload included an exploit for CVE-2020-1337, the same code available in Metasploit. For impact, Citrus disguised a Group Policy deployment as Kaspersky software, disabled Defender through the registry and encrypted systems with a Sn00py-family trojan. Kaspersky noted shared tools and, in some incidents, shared compromised infrastructure with Toy Ghouls, another Russian-speaking group that targets Russian companies.

── more in #ai-safety 4 stories · sorted by recency
── more on @kaspersky 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/citrus-ransomware-us…] indexed:0 read:1min 2026-11-11 · —