Ken Underhill

EchoGram is a new attack that can silently flip AI guardrail decisions and bypass safety checks.

ShadowMQ exposes how insecure code reuse can quietly spread dangerous vulnerabilities across the AI ecosystem.

The COM’s rise highlights how attackers increasingly exploit identity and trust to drive modern cybercrime.

A critical FortiWeb path traversal flaw is being actively exploited to create rogue admin accounts on unpatched devices worldwide.

A critical flaw in Imunify360 allowed attacker code to run during scans, putting millions of websites at risk.

Anthropic uncovered the first large-scale cyber espionage campaign powered largely by autonomous AI.

The cybersecurity space is constantly changing. Discover the cybersecurity trends of 2025 — and how security teams are simplifying complexity through clarity, context, and control.

GitLab has released urgent fixes for vulnerabilities that allow prompt injection and data exposure across its platform.

A two-year campaign quietly flooded npm with 43,000 dormant packages, exposing major supply-chain security gaps.

New runC vulnerabilities allow potential container escapes and host takeover, putting Docker, Kubernetes, and cloud-native environments at risk.

SAP’s latest emergency patches reveal how one critical flaw in core management systems can expose an entire enterprise to takeover.

A patched SSRF flaw in ChatGPT’s Custom GPTs exposed how AI features can unintentionally reveal sensitive cloud metadata.