Computer scientists develop a new AI tool that rivals AlphaFold 3 in mapping RNA

The same family of artificial intelligence that powers today's image generators is now being aimed at one of biology's ...

Malicious PyPI packages give hackers control of Telegram bot servers

A campaign active since last November has been targeting Python developers building Telegram bots with trojanized Pyrogram ...
Microsoft

Securing AI agents: When AI tools move from reading to acting

MCP tool poisoning turns trusted AI agents into a control plane for data loss. Learn how threat actors manipulate tool ...

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 ...
HotHardware

Claude AI Reviewed An MRI And Challenged A Doctor's Diagnosis, Can It Be Trusted?

Software developer and Hunter.io co-founder Antoine Finkelstein recently put an increasingly capable class of AI tools to an unusual test, asking Claude Code to analyze his shoulder MRI and weigh its ...
SecurityWeek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
TMCnet

HiddenLayer Joins Databricks Unity AI Gateway Ecosystem to Bring AI-Native Security to Enterprise AI Workloads

Building on its Unity Catalog integration, HiddenLayer is working with Databricks to extend model security, AI threat ...

Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers

In 2025 and 2026, several independent sources have highlighted the same trend: Prompt injection remains one of the most ...

Snyk launches Evo Agentic Development Security to police AI coding agents

Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence ...