AI Recommendation Poisoning: How ‘Ask AI’ Buttons Silently Alter LLM Memory
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
The rapid evolution of AI is creating pressure on security leaders to adopt AI tools, but not all AI is suited for…
Push Security provides an AI-native browser security platform that detects and stops advanced browser-based attacks, including device code phishing. Their agentic threat…
NVIDIA, along with 36 other organizations including Microsoft, Cisco, Cloudflare, CrowdStrike, Hugging Face, IBM, Palo Alto Networks, Red Hat, and the Linux…
ThreatBook is a cybersecurity firm that detected in-the-wild exploitation of CVE-2026-16723 starting July 22, 2026. It added detection support two days prior.
The Corelight Open NDR Platform combines comprehensive network visibility with deep behavioral analytics to provide security teams with actionable context and evidence-backed…
Modern Security Operations Centers (SOCs) face an escalating threat landscape where AI-equipped attackers, such as those using the autonomous exploit engine Claude…
Red Canary reported ACR Stealer delivery through fake Claude Code pages on GitLab and fake CAPTCHAs, with ACR Stealer entering its top…
CarbonBlack (now part of VMware) provides endpoint security and threat detection solutions. Miasma malware avoids systems with CarbonBlack installed.
Google and Microsoft have removed the ModHeader browser extension from their respective web stores after security researchers discovered a dormant browsing-history collector…