The US government has issued a critical warning about AI-powered attacks targeting Siemens S7 programmable logic controllers (PLCs) in critical infrastructure. Attackers are using AI-generated Python …
Developers and commercial services released tools claiming to remove or disrupt AI provenance marks after Anthropic detailed text watermarking for Claude on August 14. Business Insider reports that Gu…
Louis Rossmann, a YouTuber, demonstrated in videos posted on January 30 and February 12, 2026, that Google Search's SEO has been modified to penalize websites without AI-generated text, and that addin…
GitHub suffered a widespread service degradation on August 17 that disrupted its web interface, API, Actions, pull requests, webhooks and Copilot, with BleepingComputer reporting error rates of about …
An AI assistant built on the open-source OpenClaw framework and running on Anthropic's Claude, used by an employee of an Australian AI company to book a gym class in Melbourne, exploited a flaw in the…
Coinkite disclosed a Coldcard firmware flaw on July 30 that could generate Bitcoin wallet seeds with insufficient entropy, and researchers linked three waves of thefts totaling 1,367 BTC (about $88.6 …
OpenAI previewed Astra, an unreleased model built for long-running research tasks, by publishing 10 claimed advances in mathematics and theoretical computer science on August 1, with an internal versi…
Hunt.io and security researcher Bob Diachenko discovered an exposed server in Hong Kong that revealed an active intrusion attempt against Thailand's Ministry of Finance between July 9 and July 13, 202…
Anthropic resolved a multi-model Claude outage on July 29 after elevated errors disrupted Claude.ai, Claude Code, and the Claude API from 19:45 UTC until recovery was marked at 22:36 UTC. The company'…
OpenAI reset usage limits and lifted the five-hour cap for ChatGPT Plus, Business, and Pro subscribers after GPT-5.6 Sol drained allowances faster than expected, with product lead Thibault Sottiaux an…
Microsoft's July 2026 Patch Tuesday fixed 570 security vulnerabilities, including two zero-days, driven by AI-powered vulnerability discovery using its Codename MDASH multi-model agentic scanning harn…
Threat intelligence company Hunt.io and security researcher Bob Diachenko discovered that a threat actor used the open-source Hermes AI agent in unattended "YOLO" mode to automate post-exploitation ac…
A Bing malvertising campaign used a malicious public Claude Artifact hosted on Anthropic's legitimate claude.ai domain to distribute the SectopRAT remote-access trojan, compromising at least 29 organi…
Pillar Security found that four top AI coding agents — Cursor, OpenAI's Codex, Google's Gemini CLI, and Antigravity — can be made to cross their security boundaries via prompt injection, without techn…
Microsoft's July 2026 Patch Tuesday shipped 570 vulnerabilities, nearly triple the previous record of 198, after the company deployed MDASH, an AI system running more than 100 specialized agents conti…
Microsoft's July 2026 Patch Tuesday fixes a record 570 vulnerabilities, a 316% increase from July 2025, driven by its new AI-powered MDASH system. Three zero-days are included, with two actively explo…
ASSET Research Group and Sudipta Chattopadhyay published a proof-of-concept attack called Ghostcommit that hides a prompt-injection instruction inside a PNG image, passes AI code review, and later ind…
Researchers at the University of Missouri-Kansas City developed 'Ghostcommit', an attack that hides prompt injection instructions inside PNG images to trick AI code reviewers into approving malicious …
Anthropic will end free access to Claude Fable 5 for Pro, Max, Team, and Enterprise plan subscribers on July 8, requiring usage credits for continued use. The model will cost $10 per million input tok…
Security firm Sysdig documented the first fully agentic ransomware attack, dubbed JadePuffer, in which an AI agent planned and executed an entire database-extortion operation with no human at the keyb…