JADEPUFFER exploits Langflow CVE-2025-3248 to deploy ENCFORGE ransomware against AI model weights, vector indexes, and training data on the host.
Microsoft's newly released Agent Framework Harness packages the loops, planning, memory, context management and safety controls that developers previously had to assemble around AI models themselves.
Researchers escaped the sandboxes in Cursor, Codex, Gemini CLI and Antigravity by having the AI agent write files that trusted host tools later run. Multiple CVEs, patches, and Google downgrading two ...
Discover how the Rogue Agent vulnerability in Google Dialogflow CX enabled persistent AI agent compromise, data exfiltration, ...
A single misconfigured server has exposed the complete toolkit of an active a three-actor phishing ecosystem. According to ...
In this useful Tools & Resources article, the authors describe a new cryogenic light microscopy design and characterize its temperature and spatial stability. This compelling system avoids the ...
As governments, critical infrastructure operators, and software organizations increasingly integrate autonomous AI agents into security operations, the Friendly Fire research highlights an unresolved ...
An exposed WP-SHELLSTORM server revealed tools, logs, cloud credentials, and thousands of webshells used in a large website hacking campaign.
Securing the modern enterprise is no longer about patching individual gaps. Agentic Endpoint Security (AES) is now a ...
A Russian-speaking threat actor known as "bandcampro" used Google's open-source Gemini CLI AI tool as a hacking agent and to ...