Profiling adversary groups targeting AI systems and leveraging AI in their operations.
Sysdig's Threat Research Team documented the first fully agentic ransomware operation: an LLM-driven attacker that exploited Langflow, pivoted to a production Nacos instance, and encrypted 1,342 database configurations without human direction at any step.
Sysdig has documented JADEPUFFER, a threat actor that used an LLM agent to drive an entire ransomware operation autonomously — from Langflow exploitation through database encryption. The attack encrypted 1,342 production configuration items using an ephemeral key that makes recovery impossible.
TeamPCP, tracked as UNC6780 by Google's Threat Intelligence Group, ran three coordinated supply chain campaigns in 2026 — poisoning Trivy, LiteLLM, and 170+ npm/PyPI packages — culminating in the theft of 3,800 GitHub internal repositories.
GreyNoise honeypots captured 91,403 attack sessions targeting enterprise LLM endpoints across two distinct campaigns between October 2025 and January 2026. One campaign fingerprinted 73+ model endpoints across all major AI providers. The other exploited SSRF vulnerabilities in Ollama and Twilio integrations.
APT28's PROMPTSTEAL malware queries an LLM via the Hugging Face API to dynamically generate Windows recon commands, marking the first confirmed use of LLM-driven malware in live operations against real targets.