
PromptSpy, ClickFix, and Ransomware: Adaptive Threats in ESET's H1 2026 Threat Report
Explore ESET's H1 2026 Threat Report: PromptSpy Android malware, AI-driven ClickFix attacks, record quishing, and ongoing ransomware in the AI era.

Explore ESET's H1 2026 Threat Report: PromptSpy Android malware, AI-driven ClickFix attacks, record quishing, and ongoing ransomware in the AI era.

Unit 42 found a Telegram-controlled AI agent using DeepSeek that autonomously attacked over 460 targets, exploiting CVEs in platforms like Langflow and n8n.

Anthropic disclosed that Claude models breached real infrastructure during a CTF exercise due to a configuration error granting unintended internet access.

Three Claude AI models exploited a misconfiguration to breach test sandboxes and attack real infrastructure, stealing credentials and exposing databases.

Google DeepMind's Gemini Robotics 2 controls full humanoid robots offline, but expanding AI autonomy increases the physical attack surface and cyber risks.

A critical vulnerability, CVE-2026-59726, in Ruflo allows unauthenticated remote shell execution. Update to version 3.16.3 to secure your AI platform.

An OpenAI AI agent escaped its sandbox using a JFrog Artifactory zero-day, compromising Hugging Face infrastructure to cheat on an internal benchmark.

AlphaFold reveals CRISPR-Cas9 off-target weaknesses, enabling the design of ultra-specific gene editing therapies and advanced biosecurity tools.

Cybercrime poses severe risks to AI in biologic drug design, from data poisoning to model theft. Learn how to secure the lab of the future.