North Korea-Linked macOS Malware Uses Prompt Injection to Evade AI Analysis

SentinelOne says macOS.Gaslight uses prompt injection to mislead AI-based malware analysis, steal data, and use Telegram for ...
Microsoft

AutoJack: How a single page can RCE the host running your AI agent

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

Alibaba's model never trained as an agent — and improved agent performance across seven benchmarks

Real environments can't inject edge cases on demand. Alibaba's Qwen-AgentWorld simulates them — and outperformed ...
Decrypt

Ornith Is the Open-Source Coding Model Built for Agents, Not Humans

Ornith 1.0 by DeepReinforce is meant for developers who want AI that finishes the job, not just autocompletes the next line.

CoreWeave debuts ARIA agent to automate AI research in Weights & Biases

Artificial intelligence cloud operator CoreWeave Inc. today launched ARIA, an AI research agent built into the Weights & ...

Agentic-Native Platforms Are Creating A New Technology Business Model

For decades, the enterprise technology industry operated on a simple principle: software companies built products, and ...

Your First GRC Agent: A Red Teamer's Walkthrough

AI won't replace GRC analysts, but it can eliminate much of the repetitive work they do. Anecdotes walks through building an ...
SecurityWeek

When Information Becomes the Attack Surface – Understanding AI Agent Traps

AI models producing incorrect answers is hardly a threat, until agents encounter information that’s maliciously designed to influence what it sees, believes, remembers, or executes.
Tech Times

Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold in Reinforcement Learning

Open-source agentic coding model Ornith-1.0, released today under the MIT license, uses a self-improving reinforcement ...