More Capable AI, Not Enough Guardrails
More Capable AI, Not Enough Guardrails Pierluigi Paganini September 10, 2026 AI agents are gaining real-world access faster than safeguards...
AndyC
Andy Curtis is an award-winning security consultant, researcher and public speaker. He has been working in the computer security industry since the early 1990s, having been employed by state and federal government, leading healthcare and banking providers across three continents. He has given talks about computer security for some of the world’s largest companies, worked with law enforcement agencies on investigations into hacking groups, and is a regular voice on TV and radio explaining IT security threats.
‘Anne Hathaway’ admits leading $245 million crypto theft gang that spent a fortune on nightclubs, watches, and luxury cars
Here's a tip for any budding cybercriminals out there.If you're going to steal a quarter of a billion dollars worth...
How Apple is trying to normalize always-on AI
if ( !emtpy($headline_subheadline ) ) : ?> Apple’s Audio Intelligence knows what you are saying, but doesn’t hold it against...
Google Play Early Access Abused to Push Thousands of Deceptive Android Apps
Ravie LakshmananSep 10, 2026Mobile Security / Artificial Intelligence Bad actors are misusing Google Play's Early Access program to push deceptive...
Check Point Discloses Two 9.8-Rated VPN Certificate Flaws Enabling Unauthenticated RCE
Check Point has patched two critical vulnerabilities in the way its firewall and management products handle VPN certificates. The company...
PaperCut Attacker Uses Hundreds of AI Agents to Compromise 440+ Instances
A suspected Russian-speaking cyber actor has been attributed to the use of artificial intelligence (AI) to devise exploits targeting a...
Gigabud Creates Android Work Profiles to Hide From Banking App Malware Checks
The Gigabud banking trojan now installs a second Android app that creates a work profile on an infected phone and...
Qualcomm’s next Snapdragon mobile chip comes into focus with on-device AI
if ( !emtpy($headline_subheadline ) ) : ?> Qualcomm is betting that smarter local AI starts with keeping more compute, memory...
Clearview AI Is Testing an AI Tool That Would Let Cops Unearth Your Life Online
InquiryIQ, a previously unreported prototype, tested a model from xAI, maker of Grok, to surface associates, social accounts, and other...
A New Claude ‘s Sandbox Failure Shows How AI Can Rationalize Real-World Harm
A New Claude ‘s Sandbox Failure Shows How AI Can Rationalize Real-World Harm Pierluigi Paganini September 10, 2026 Claude models...
U.S. CISA adds Microsoft Windows, N-able N-central, and Adobe flaws to its Known Exploited Vulnerabilities catalog
U.S. CISA adds Microsoft Windows, N-able N-central, and Adobe flaws to its Known Exploited Vulnerabilities catalog Pierluigi Paganini September 10,...
AIs Compress Exploit Timeline
AIs Compress Exploit Timeline Give an AI agent a mere rumor of an exploit, and it’s enough for them to...
CISA Flags Exploited Cisco, Citrix, Fortinet Flaws, Sets Sept. 12 Federal Patch Deadline
Ravie LakshmananSep 10, 2026Vulnerability / Network Security The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Wednesday added three flaws,...
Nearly 1 in 10 Exposed LiteLLM Gateways Accepted the Example “sk-1234” Admin Key
Nearly one in ten of the internet-facing LiteLLM servers that Wiz Research scanned in February accepted sk-1234, the example admin key in LiteLLM's...
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence (AI) model broke into real third-party systems, marking...
