A forensic tool for backdoored code completions in AI assistants
Developers lean on AI coding assistants for a growing share of their daily work, letting the tools predict the next few lines and accepting many suggestions with a quick …
Nearly half of open-source AI projects never reach production
Open models are moving into production across more organizations, and the work of securing those deployments increasingly extends beyond the model weights. Mozilla’s The State …
Prompt injection is becoming the XSS of the web agent era
Autonomous web agents read whatever a page displays, and much of that content comes from strangers. Product reviews, seller listings, and advertisements sit beside trusted …
Russian cybercriminal used jailbroken Gemini CLI to rebuild botnet infrastructure in six minutes
A Russian-speaking threat actor known as “bandcampro” used a jailbroken Gemini CLI, Google’s open-source terminal-based AI agent, to deploy and operate a …
GPT-Red beat human red teamers on a prompt injection test
GPT-Red is an automated red-teaming model that OpenAI trains to find prompt injection weaknesses. It works the way a human red-teamer does. It sends a prompt, watches how a …
AI-driven bug hunting fuels record Microsoft Patch Tuesday
Microsoft has released patches for 570+ vulnerabilities on July 2026 Patch Tuesday, including two that are being leveraged by attackers (CVE-2026-56155 and CVE-2026-56164), …
AWS retools Security Hub for AI and multicloud threats
AWS added AI workload protection and Microsoft Azure security monitoring to Security Hub, its centralized security platform for collecting and prioritizing security findings …
The MDR renewal question: What changes when AI can handle the alerts
For most of the past decade, the managed detection and response (MDR) decision was a simple one: teams that couldn’t staff a 24/7 SOC outsourced detection and response …
An AI overthinking attack can tie a robot up for over a minute
Robots that read the world through cameras now lean on large vision-language models to interpret what they see and decide what to do next. These models handle images and text …
AI used to help plan the break-in, now it’s doing the break-in
Over the past twelve months, researchers documented intrusions in which AI ran exploitation workflows autonomously, generating thousands of commands across dozens of sessions …
The best defense against AI attacks turns out to be a skeptical human
Analysts across the security industry now run generative AI through their daily work, from log triage to incident write-ups. Active use in cybersecurity strategy reached 78% …
A hardware security AI assistant that checks chips for hidden backdoors
Chip designers license blocks of circuitry from outside vendors and drop them into larger products. A single processor can carry components from a range of suppliers, each …
Featured news
Resources
Don't miss
- The TASK#STOMP Windows backdoor takes Wi-Fi passwords, screenshots, and business files
- North Korea’s job interview scam runs both ways
- Hackers exploit Gyazo server flaw to steal 23.6 million user records
- Know what was tested before your SAP ECC migration goes live
- Gopass: Open-source command-line password manager for teams