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 ...
How-To Geek on MSN

I used NotebookLM to wrangle a month of research—here's where it fell apart

This AI research tool saved me hours organizing technical notes, but it has one fatal flaw at scale.
Bleeping Computer

ChocoPoc malware delivered via trojanized exploits on GitHub

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...
Visual Studio Magazine

New GitHub Switch Limits Repo Issue Creation to Collaborators Only

After publicly touting pull request limits as a way to cut maintainer noise, GitHub is taking the same idea further with a new setting that lets repository admins restrict issue creation to ...
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.
Rock Paper Shotgun

"Low-effort slop": The creators of the Godot engine behind Slay the Spire 2 are cracking down on "vibe-coding" and now require genAI disclosures

The Godot Foundation have announced a crackdown on genAI code, including mandatory disclosures, following a wave of ...
Infosecurity Magazine

Researcher Behind 'Exploitarium' Explains Release of Undisclosed Zero-Day Exploits

Infosecurity spoke with the researcher who dumped over 30 proof-of-concept exploits without disclosing the vulnerabilities ...
eLife

TopoMetry systematically learns and evaluates the latent geometry of single-cell data

A framework for analyzing single-cell genomics data, in which geometrical properties are harnessed to obtain insights on cellular diversity, including precise clustering, clear visualizations, and ...