Malicious AI agent skills can slip past the scanners built to stop them
Developers who build with AI coding agents grab capabilities off public marketplaces the same way they grab packages from npm or PyPI. The add-ons are…
Author: Cybernoz
Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It
Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker’s code on your own machine instead. That…
UK’s largest businesses dangerously exposed to cloud outages
Whether arising from a cyber attack or another form of disruption, a 24-hour outage affecting major Amazon Web Services (AWS) or Microsoft Azure cloud regions…
SpaceX applies to launch 100,000 Gen3 Starlink satellites
SpaceX has filed an application with the US Federal Communications Commission (FCC) for authority to launch and operate up to 100,000 third-generation Starlink satellites, the…
Unpatched Backdoor in Tenda Firmware Grants Admin Access to Devices
A security researcher has discovered an undocumented backdoor in multiple Tenda firmware versions that provides attackers with administrative access to a device’s web management interface.…
CISA Deploys Anthropic’s Mythos AI to Hunt Vulnerabilities in U.S. Government Code
CISA Deploys Anthropic’s Mythos AI to Hunt Vulnerabilities in U.S. Government Code Pierluigi Paganini July 08, 2026 CISA is using Anthropic’s Mythos AI to scan…
Sophisticated threat campaign pushes Cisco to the very edge
A monthslong exploitation wave against Cisco SD-WAN systems raises larger questions about trust and the insecurity of network infrastructure. Source link
GitHub’s public APIs are becoming an enterprise reconnaissance tool
Attackers use a mix of data exfiltration agents with names like GitHub-Company-Scraper, GitHub-Scraper-Tool/1.0., and GitHubAnalytics/1.5,designed to blend into normal data analysis traffic. The bulk of…
Designing for the inevitable: System prompt leakage and mitigations in generative AI applications
System prompts form the foundation of generative AI applications. A system prompt is a collection of instructions and operational context provided to a large language…
When AI-Accelerated Discovery Outruns Patching, Exploitability Proof Decides What Gets Fixed First
Why Qualys joined the Athena coalition, and what it means for how you prioritize risk. Qualys is proud to have joined Athena, the industry coalition…
Fake Paysafe, Skrill SDKs on NPM and PyPi steal credentials
Malicious packages on the Node Package Manager (npm) and the Python Package Index (PyPI) delivered stealer malware to developers and users of Paysafe, Skrill, and…
Claude, Cursor, and Codex Trigger Endpoint Security Rules Used to Catch Hackers
AI coding agents such as Claude Code, Cursor, and OpenAI Codex are increasingly appearing in enterprise environments, and new telemetry shows they are unintentionally triggering…