New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email
Give an AI assistant a memory and access to your inbox, and you hand an attacker a way to rewrite what it thinks it knows about you. A single email can trick that agent into saving a false "fact" about the user, hide the change, and quietly steer its answers in later sessions. W
Google and Microsoft Pull ModHeader With 1.6 Million Installs After Dormant Collector Found
Google and Microsoft have pulled ModHeader, a popular header-editing extension with roughly 1.6 million installs across Chrome and Edge, after researchers found a hidden browsing-history collector built into its official store version. The collector was dormant. An empty allow-l
How Pentera Turns AI Security Workflows into Validation Engines
AI security agents are starting to influence real security decisions. They summarize findings, prioritize remediation, recommend next steps, and help teams move faster. But most still rely on fragmented risk signals: scanner output, severity scores, threat intelligence, configura
Researchers Say Claude for Chrome Flaw Lets Rogue Extensions Trigger Gmail Reads
Any other browser extension that can run a script on claude.ai can still trigger Claude for Chrome tasks aimed at your Gmail, your latest Google Doc and its comments, and your Calendar. Both this and ClaudeBleed need a rogue extension that can already run a script on claude.ai;
Inside the 2026 SMB threat landscape: From phishing and scams to fake AI tools
Kaspersky researchers analyze the threat landscape for SMBs in 2026: the rise of attacks involving fake AI tools, phishing schemes, and data sold on the dark web.
OpenClaw: risks for the users and how to mitigate them
Researching OpenClaw vulnerabilities, malicious skills, and other security issues with the popular agent, and providing tips on how to mitigate them.
Missed incidents, persistent threats, and response gaps: Insights from compromise assessment projects
Kaspersky Compromise Assessment specialists analyze trends from the service's 2025 projects and provide tips on how to enhance your organization's security.
When “Hi, This Is IT” Comes Through Microsoft Teams
Attackers are increasingly targeting collaboration platforms like Microsoft Teams. Learn the risks and key steps to strengthen your organization's security. The post When “Hi, This Is IT” Comes Through Microsoft Teams appeared first on Unit 42.
Blinding the Watchmen: Abusing Cloud Logging Services for Defense Evasion and Visibility
Unit 42 research examines attack scenarios targeting cloud logging services. Learn how to defend against log manipulation and defense evasion. The post Blinding the Watchmen: Abusing Cloud Logging Services for Defense Evasion and Visibility appeared first on Unit 42.
Trust No Skill: Integrity Verification for AI Agent Supply Chains
Protect enterprise AI agents from supply chain risks by auditing third-party skills for hidden vulnerabilities and multi-stage attack chains. The post Trust No Skill: Integrity Verification for AI Agent Supply Chains appeared first on Unit 42.
Tracing Digital Intent: New MacOS Tahoe 26 Artifact Discovered
Unit 42 has discovered a new macOS Tahoe 26 forensic artifact that tracks user menu selections across the operating system. Learn more here. The post Tracing Digital Intent: New MacOS Tahoe 26 Artifact Discovered appeared first on Unit 42.
Inside the Modern SOC: The 72-Minute Race
Attackers can move from access to exfiltration in 72 minutes. Learn how modern SOC teams close the speed gap with Unit 42's AI-driven automation, threat hunting, MDR and Managed XSIAM. The post Inside the Modern SOC: The 72-Minute Race appeared first on Unit 42.