Severity: HighIncidentMCP/tool abuse
Threat Actor Leverages Google's Gemini CLI for Botnet Command and Credential Compromise
Live intelligence. Items are aggregated from public sources and summarised automatically. Always verify against the linked source before acting.
A Russian-speaking attacker delegated botnet operations to Google's open-source Gemini CLI tool, using the LLM interface to automate password cracking and establish control over a dental clinic network spanning eight machines. Analysis of 200 Gemini CLI session logs spanning March–April 2026 revealed the actor's use of AI-augmented attack workflows to accelerate compromise and persistence activities.
What to do
Restrict LLM tool access via network policy and monitor for anomalous AI-assisted attack patterns in your environment logs.
Mapped framework pillars
Sources
#LLM abuse#botnet#credential compromise#Gemini CLI#threat automation#healthcare