AI agents need broad access to be useful, but traditional access controls cannot determine whether an action aligns with a user’s intent. Varonis explains how Agent IBAC detects intent drift and enforces real-time guardrails to keep agents within their intended boundaries. […]
Weaponized Email AI Assistants Could Help Attackers Hijack Accounts
Researchers demonstrate how attackers could abuse built-in email chatbots to evade detection, impersonate trusted employees, compromise executive accounts, and facilitate financial fraud.
The post Weaponized Email AI Assistants Could Help Attackers Hijack Accounts appeared first on SecurityWeek.
Zenity Raises $125 Million in Series C Funding
The AI security company will invest in product innovation, global expansion, and customer experience.
The post Zenity Raises $125 Million in Series C Funding appeared first on SecurityWeek.
Keyv-Linked npm Worm Poisons Hundreds of Packages, Plants Claude Code and VS Code Hooks
A credential-stealing npm worm that first appeared in keyv@6.0.0 spread beyond the Keyv and Cacheable namespaces into hundreds of packages across multiple organizations on August 4, 2026.
SafeDep verified 353 poisoned versions across 79 package names in the npm registry. Its monitoring put the wider footprint at 442 versions across 353 names, while Aikido later reported at least 868 packages
Fake Adobe and Zoom Updates Install ScreenConnect for Persistent Remote Access
Cybersecurity researchers have disclosed details of an active, multi-wave campaign that employs social engineering lures themed around Adobe and Zoom software updates, business document reviews, and system maintenance utilities to stealthily deploy Remote Monitoring and Management (RMM) programs like ConnectWise ScreenConnect.
The campaign has been codenamed SMOKE#SCREEN by Securonix Threat
TP-Link Omada ZTP Vulnerabilities Chain Into Full Network Takeover
Forescout researchers have found 15 new vulnerabilities in the TP-Link Omada networking ecosystem.
The post TP-Link Omada ZTP Vulnerabilities Chain Into Full Network Takeover appeared first on SecurityWeek.
When Vibe Hacking Turns AI into the Junior Hacker Every Adversary Always Wanted
The cybersecurity industry has spent decades assuming that offensive capability scales with technical expertise.
That assumption is starting to break.
Security teams have long estimated risk by ranking attacker sophistication. Nation-state actors sat at one end. Organized criminal groups followed. Inexperienced attackers, dismissed as “script kiddies,” sat at the other end, running public
Google Deletes 3 ADK AI Workflows After Malicious GitHub Issue Could Trigger Privileged Agent
Google deleted three AI agent workflows from its Agent Development Kit (ADK) Python repository. Pillar Security showed that a public GitHub issue could manipulate a triage agent into triggering a privileged code-fixing agent.
The researchers said the public agent could be prompt-injected into posting /adk-issue-fix as adk-bot. They identified the bot as a collaborator, so that comment satisfied
Gemini Agent-to-Agent Attack Method Exposed Secrets, Enabled Pull Request Tampering
A crafted prompt to a low-privilege Google ADK agent could be used to pass a malicious hand-off comment to a privileged agent.
The post Gemini Agent-to-Agent Attack Method Exposed Secrets, Enabled Pull Request Tampering appeared first on SecurityWeek.
New cPanel Critical Flaw Could Let Hosting Customers Run SQL as Database Root
cPanel has patched a flaw that let an authenticated hosting customer execute SQL in the database’s root context, crossing the privilege boundary between a cPanel account and the server’s administrative database identity. It shipped in a targeted security release that closes two other routes past account boundaries.
The database bug is tracked as CVE-2026-58048 (CVSS 4.0 score: 9.4) and affects