Cybersecurity researchers have disclosed details of a new method for exfiltrating sensitive data from artificial intelligence (AI) code execution environments using domain name system (DNS) queries.
In a report published Monday, BeyondTrust revealed that Amazon Bedrock AgentCore Code Interpreter's sandbox mode permits outbound DNS queries that an attacker can exploit to enable interactive shells
The ransomware operation known as LeakNet has adopted the ClickFix social engineering tactic delivered through compromised websites as an initial access method.
The use of ClickFix, where users are tricked into manually running malicious commands to address non-existent errors, is a departure from relying on traditional methods for obtaining initial access, such as through stolen credentials
AI agents are autonomous actors with real access to data and systems, not just copilots. Token Security explains why identity-based access control is critical to prevent misuse and data exposure. [...]
The LeakNet ransomware gang is now using the ClickFix technique for initial access into corporate environments and deploys a malware loader based on the open-source Deno runtime for JavaScript and TypeScript. [...]
A majority of security leaders are struggling to defend AI systems with tools and skills that are not fit for the challenge, according to the AI and Adversarial Testing Benchmark Report 2026 from Pentera.
The report, based on a survey of 300 US CISOs and senior security leaders, examines how organizations are securing AI infrastructure and highlights critical gaps tied to skills shortages and
Microsoft has shared guidance to fix C:\ drive access issues and app failures on some Samsung laptops running Windows 11, versions 25H2 and 24H2. [...]
Microsoft is working to address a known issue that renders the classic Outlook email client unusable for users who have enabled the Microsoft Teams Meeting Add-in. [...]
Le 16 mars 2026, Nvidia a lancé NemoClaw, une couche de sécurité et de gouvernance qui vient se superposer à OpenClaw. Avec ce projet, l'entreprise américaine espère convaincre les entreprises que l’ère des agents IA peut enfin se concilier avec la sécurité.
North Korean threat actors have been observed sending phishing to compromise targets and obtain access to a victim's KakaoTalk desktop application to distribute malicious payloads to certain contacts.
The activity has been attributed by South Korean threat intelligence firm Genians to a hacking group referred to as Konni.
"Initial access was achieved through a spear-phishing email disguised as a
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Monday added a medium-severity security flaw impacting Wing FTP to its Known Exploited Vulnerabilities (KEV) catalog, citing evidence of active exploitation.
The vulnerability, CVE-2025-47813 (CVSS score: 4.3), is an information disclosure vulnerability that leaks the installation path of the application under certain conditions
The GlassWorm malware campaign is being used to fuel an ongoing attack that leverages the stolen GitHub tokens to inject malware into hundreds of Python repositories.
"The attack targets Python projects — including Django apps, ML research code, Streamlit dashboards, and PyPI packages — by appending obfuscated code to files like setup.py, main.py, and app.py," StepSecurity said. "Anyone who runs
Depuis plusieurs jours, des internautes signalent une nouvelle campagne de phishing par SMS ciblant des numéros français. Sa particularité : elle s'appuie sur une photo générée par intelligence artificielle pour tenter de tromper ses victimes.
Some weeks in security feel normal. Then you read a few tabs and get that immediate “ah, great, we’re doing this now” feeling.
This week has that energy. Fresh messes, old problems getting sharper, and research that stops feeling theoretical real fast. A few bits hit a little too close to real life, too. There’s a good mix here: weird abuse of trusted stuff, quiet infrastructure ugliness,
Last week's cyberattack on medical technology giant Stryker was limited to its internal Microsoft environment and remotely wiped tens of thousands of employee devices. [...]
CISA warned U.S. government agencies to secure their Wing FTP Server instances against an actively exploited vulnerability that may be chained in remote code execution attacks. [...]
Companies House, a British government agency that operates the registry for all U.K. companies, says its WebFiling service is back online after it was closed on Friday to fix a security flaw that exposed companies' information since October 2025. [...]
Connexion
