Inside a New Wave of LLM Hijacking on AWS
On November 26, 2024, Wiz Research identified a threat actor we track as JINX-2401 attempting to hijack LLM models across multiple AWS environments. With the…
Author: Cybernoz
Pokémon Center data breach exposes customer info, cancels some orders
Pokémon Center is notifying customers in the United Kingdom and Germany that it suffered a third-party data breach after hackers stole customer personal and order…
Pokémon Center Confirms Data Breach
Pokémon Center has begun notifying customers in the United Kingdom and Germany that their personal information was exposed in a third-party data breach, and that…
Malicious Google Apps Script Profiles Crypto Victims Before Delivering Signed Windows Malware
A targeted cryptocurrency intrusion has exposed how Google-hosted Apps Script pages can be weaponized to profile prospective victims before delivering signed Windows malware. The campaign…
Police bust cybercrime ring accused of stealing €30 million in four-day spree
German and Brazilian police dismantled an international bank fraud ring blamed for a €30 million cyberattack on a German financial institution, arresting four people in…
Why Facebook’s war on ad blockers could help scammers
Reports that uBlock Origin is stepping back from the never-ending effort to filter Facebook ads are a reminder that ad blocking is no longer only…
Critical GitLab GraphQL Flaw Could Let Unauthenticated Attackers Delete Public Projects
Swati KhandelwalAug 17, 2026Vulnerability / DevOps GitLab has released security updates to address a critical vulnerability impacting its Community Edition (CE) and Enterprise Edition (EE)…
Lanarkshire gets £300m to fund AI growth zone
More jobs, investment and training opportunities are on the way for Lanarkshire, Scotland, as the AI growth zone secures a landmark £300m investment package and…
Apple to change app data consent rules
In summary Germany’s federal cartel office has closed a years-long investigation after Apple agreed to change how app developers use personal data for targeted advertising.…
Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware
Anthropic has published new research showing that Claude-based AI agents, when placed in situations with competing objectives, deployed self-replicating malware against one another. The finding…
LiteLLM Supply-Chain Attack – Technology, Banking and Healthcare the Most Affected
LiteLLM Supply-Chain Attack – Technology, Banking and Healthcare the Most Affected Pierluigi Paganini August 17, 2026 The SANDCLOCK LiteLLM supply-chain attack exposed credentials across 2,038…
How AI Builders Will Get Hacked
If you are building stuff with AI I have a critical security recommendation for you. Create a continuously-running security testing system that: Maintains a list…