A crafted prompt to a low-privilege Google ADK agent could be used to pass a malicious hand-off comment to a privileged agent.
Critical cPanel Vulnerability Allows Execution of SQL Commands as Root User
A critical privilege-escalation flaw in cPanel & WHM has been disclosed that could allow authenticated hosting users to execute arbitrary SQL commands…
Europol and Frontex strengthen cooperation with new Working Arrangement
The new arrangement replaces the agreement signed in 2015 and reflects the significantly expanded mandates that both agencies have received in recent…
Threats Making WAVs – Incident Response to a Cryptomining Attack
Guardicore security researchers describe and uncover a full analysis of a cryptomining attack, which hid a cryptominer inside WAV files. The report…
Europol-led action against nihilistic violent extremist network “The Com”
An estimated 4 340 URLs related to nihilistic violent extremism were referred during the initiative organised by Europol’s EU Internet Referral Unit – EU…
Midnight Blizzard Hijacks Hotel Wi-Fi to Infect Travelers and Steal Cloud Credentials
Travelers using hotel Wi-Fi are facing a new threat linked to Midnight Blizzard, a Russia-linked threat group known for targeted credential theft. The…
Migrant smuggling network using rental cars dismantled across the Balkans
Led by the Greek authorities and supported by Europol, the investigation targeted a criminal network composed mainly of Syrian and Egyptian nationals…
Keep Your Tech Flame Alive: Trailblazer Rachel Bayley
In this Akamai FLAME Trailblazer blog post, Rachel Bayley encourages women to step into the unknown and to be their authentic selves.
Five arrests for smuggling migrants across the Bulgarian-Serbian green border
The action day led to:5 arrests (1 High Value Target, 2 police officers and 2 associates)5 locations searched;Seizures include: 3 vehicles used for…
Alibaba’s Qwen Latest AI Model To Challenge US Dominance
Alibaba’s Qwen3.8-Max, second-largest in China, achieves performance second only to models from Anthropic, tests find
Europol supports operation against amphetamine producers
As part of an extensive investigation led by the German Krefeld Public Prosecutor’s Office and Mönchengladbach Police, officers from the North…
Some Claude Chats Are Searchable on Google
And it’s personal information (alternate link ): The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on…
AI Accounts for Over Half of Cybercrime in Africa, Says Interpol
Interpol claims AI is driving a surge in cybercrime in Africa, with related losses doubling
A Malicious GitHub Issue Could Turn Google’s AI Agent Against Its Own CI/CD Pipeline
A first practical, real-world case of agent-to-agent exploitation inside a production multi-agent system, a novel attack class that turns one AI agent…
Indusface SwyftComply AI enables autonomous virtual patching for AI-discovered flaws
Indusface has announced SwyftComply AI, an autonomous vulnerability remediation solution that virtually patches vulnerabilities surfaced by AI-assisted…
Chinese Military Researchers Use AI Distillation to Train Drone and Battlefield Systems
Chinese military-linked researchers are studying ways to turn the outputs of advanced Western AI systems into smaller, cheaper models for drones,…
DOUBLECUP Uses ClickFix and Cached PNGs to Deliver CountLoader and DeviceManager RAT
A new Russian loader-as-a-service (LaaS) codenamed DOUBLECUP has been using ClickFix lures as a way to stage malware-laced PNG images in victims’ browser…
BINDCLOAK Steals Windows User and Process Tokens to Run Malware With Higher Privileges
A newly uncovered Windows backdoor is giving an East Asia-linked espionage operation a quiet way to deepen control inside targeted networks. Named…
Joinable Labs unveils Joinable Security for threat intelligence and AI-driven response
Joinable Labs launched Joinable Security, the first domain on the Joinable platform, with two products: Joinable Threat Map, a free utility that lets the…
Apache NiFi Vulnerabilities Enable Authorization Bypass Attacks
Apache NiFi users should upgrade to version 2.11.0 after the project disclosed four security vulnerabilities affecting the NiFi Web API and Parameter…
ESET introduces new AI capabilities for autonomous agent security
ESET is expanding its AI capabilities across threat detection, investigations, threat protection, and security operations, delivering added value to…
Fake AI Tool Campaign Turns Developer Interest Into Enterprise Initial Access
A new malware campaign is turning interest in artificial intelligence tools into a route for enterprise intrusion. Attackers are cloning trusted GitHub…
IT Security News Hourly Summary 2026-08-04 12h : 14 posts
14 posts were published in the last hour 10:2 : “Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI 10:2 : Decades-Old BMC Vulnerability Exposes Thousands of Data Centers to Attacks 10:2 : Apple…
“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI
Talos has collected prompt logs from threat actor endpoints running various applications, such as Claude Code, CodeX, Cursor, or Gemini. This blog is an…