Aggregator

Zenity announced runtime protection for OpenAI’s AgentKit, providing enterprise-grade enforcement that detects and blocks data leakage, secret exposure and unsafe agent behavior in real time. This launch follows Zenity Labs’ recent research exposing critical gaps in OpenAI’s AgentKit guardrails that can be bypassed through prompt injection, response obfuscation, credential exposure and other attack vectors. By adding runtime protection to AgentKit, Zenity closes these gaps by inspecting agent behavior and intent at the endpoint and enforcing … More →

The post Zenity delivers runtime protection for OpenAI’s AgentKit appeared first on Help Net Security.

You must login to view this content

You must login to view this content

You must login to view this content

You must login to view this content

Supply chain attacks targeting the JavaScript ecosystem have evolved into sophisticated operations combining domain manipulation with social engineering. On September 8, 2025, threat actors launched a coordinated phishing campaign aimed at compromising high-profile NPM developers. The attack successfully infiltrated the accounts of developer Josh Junon, known as “qix,” and targeted at least four other maintainers, […]

The post New Business Email Protection Technique Blocks the Phishing Email Behind NPM Breach appeared first on Cyber Security News.

Security researchers at the SANS Internet Storm Center have detected a significant spike in suspicious network traffic targeting Windows Server Update Services (WSUS) infrastructure worldwide. The reconnaissance activity focuses specifically on TCP ports 8530 and 8531, which correspond to unencrypted and encrypted communication channels for WSUS servers vulnerable to the recently disclosed CVE-2025-59287. This coordinated […]

The post Hackers Actively Scanning TCP Ports 8530/8531 for WSUS CVE-2025-59287 appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.