The security tool intercepts potentially dangerous agent actions, blocking clear threats and requesting human approval when intent is uncertain.
The post OpenLeash Adds a Human Check to Risky AI Agent Actions appeared first on SecurityWeek.
WordPress backup plugin flaw exposes millions of sites to takeover attacks
An SQL injection vulnerability in the All-in-One WP Migration and Backup plugin for WordPress could allow unauthenticated attackers to execute remote code and take control of affected websites. […]
Google, Anthropic, and OpenAI Unveil Cyber AI Models, Safeguards, and Access Programs
Google on Wednesday announced Gemini 3.8 Flash Cyber, which it described as its most capable cybersecurity model, and has made it available to a set of trusted defenders via a new initiative called the Fairwind Program.
“The Fairwind Program gives high-priority defenders (like governments, healthcare providers, and telecommunications services) early access to advanced models that help them
Fake Software Installers Disable Windows Update and Weaken Microsoft Defender
An active malware campaign is using bogus software-download websites to impersonate trusted vendors and distribute malicious installers.
“The campaign has targeted users looking to download popular software and has resulted in compromises across multiple organizations and industries, primarily affecting China-based operations of multinational organizations and Chinese-speaking users,” Microsoft
Hackers exploit critical JFrog Artifactory flaw to forge admin tokens
A critical authentication bypass vulnerability (CVE-2026-82329) in JFrog Artifactory is being exploited in attacks to create tokens that provide administrative access. […]
UK Moves to Block High-Risk Tech Suppliers From Critical Infrastructure
Late amendments to the Cyber Security and Resilience Bill would give ministers new powers to restrict risky technology providers as supply chain attacks intensify.
The post UK Moves to Block High-Risk Tech Suppliers From Critical Infrastructure appeared first on SecurityWeek.
Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository’s own Git configuration names a command that the agent runs on the developer’s machine, four of them still unpatched at publication.
The command executes as the user, outside the agent’s sandbox and without an approval prompt, and exploitation requires the repository to arrive
Ransomware protection for MSPs: A 6-point checklist for faster recovery
Ransomware resilience requires more than backups or endpoint detection alone. Acronis outlines six capabilities MSPs should test across client environments, from reducing exposure and detecting attacks to preserving recovery points and restoring operations quickly. […]
Malicious Apache Modules Hijack Brazilian Government Site Traffic to Push Betting Pages
A Chinese-speaking cybercrime cluster known as Gambling Goblin has been observed installing malicious Apache modules on compromised web servers run by Brazilian government and educational institutions, and using them to divert visitors to attacker-controlled pages promoting online gambling and sports betting.
Check Point Research said it has tracked the campaign since mid-2025.
The modules
BGP Hijack Delivers Malicious Virtualizor Update That Establishes Persistent Root Access
Virtualizor said hackers used a Border Gateway Protocol (BGP) hijack to divert Softaculous traffic. The hackers then used the diverted update traffic to deliver a malicious Virtualizor package to some installations. A hosting-provider account separately said 5 of its 34 checked Virtualizor hypervisors sustained root-level compromise.
The incident window ran from approximately August 28 at 20:57