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

Prompt injection remains the most effective way to compromise enterprise AI systems because it exploits the fundamental way ...

Clean GitHub repo tricks AI coding agents into running malware

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
The Hacker News

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis

SentinelOne details Gaslight, a Rust-based macOS implant linked to North Korea-aligned actors that uses prompt injection to ...
The Verge

Microsoft is threatening legal action for disclosing exploits

The company is feuding with a security researcher publicly posting vulnerabilities. The company is feuding with a security researcher publicly posting vulnerabilities. is the Verge’s weekend editor.
Ars Technica

Google publishes exploit code threatening millions of Chromium users

Google on Wednesday published exploit code for an unfixed vulnerability in its Chromium browser codebase that threatens millions of people using Chrome, Microsoft Edge, and virtually all other ...
CoinTelegraph

THORChain pauses trading after suspected $10M exploit

THORChain paused trading after ZachXBT flagged a suspected $10 million exploit spanning Bitcoin, Ethereum, BNB Chain and Base. Decentralized liquidity protocol THORChain halted trading after ...
TechSpot

A security researcher says Microsoft secretly built a backdoor into BitLocker, releases an exploit to prove it

The Epitome of WTF: A researcher known as "Nightmare-Eclipse" recently released YellowKey, a security vulnerability that allegedly enables a full bypass of BitLocker's full-volume encryption. The ...
Ars Technica

Zero-day exploit completely defeats default Windows 11 BitLocker protections

A zero-day exploit circulating online allows people with physical access to a Windows 11 system to bypass default BitLocker protections and gain complete access to an encrypted drive within seconds.
TechRepublic

Google Says Hackers Used AI to Build Zero-Day Exploit

Google says hackers used AI to help build a zero-day exploit targeting 2FA, raising concerns about AI-assisted hacking. Google says hackers used AI to help build a zero-day exploit, then stopped it ...
CNBC

Google says it likely thwarted effort by hacker group to use AI for 'mass exploitation event'

Google's Threat Intelligence Group said hackers are using AI models such as OpenClaw to uncover and exploit zero-day software vulnerabilities. The group said in a report that it had uncovered and ...
PC World

Unpatched Microsoft Defender flaw lets hackers gain admin access

PCWorld reports on the ‘RedSun’ vulnerability in Microsoft Defender affecting Windows 10, 11, and Server systems that allows attackers to gain administrative privileges. Security researcher Chaotic ...