Microsoft’s AutoJack research shows how a malicious webpage rendered by an AI browsing agent can reach local MCP services and ...
Look to these key metrics and benchmarks to evaluate the performance, capability, reliability, and safety of your AI models ...
The ability to quickly manufacture vaccines that closely match the latest flu strains could prevent thousands of hospitalizations.
Attackers are actively exploiting path traversal and SQL injection in Langflow, LangGraph, and LangChain — below where your ...
Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...
ThreatsDay Bulletin: Claude Chat Abuse, NastyC2 npm Packages, Device-Code Phishing + 25 More Stories
ThreatsDay Bulletin covers AI abuse, poisoned packages, phishing, macOS attacks, SD-WAN flaws, scams, and supply-chain ...
As black-market drugs go mainstream and legalization is within reach, entrepreneurs, investors and healthcare players are ...
IntroductionOn May 14, 2026, the Zscaler ThreatLabz team identified unusually high activity associated with the threat actor SmartApeSG to deploy malware. During our examination, we discovered ...
From package to postinstall payload: Inside the Mastra npm supply chain compromise by Sapphire Sleet
A poisoned npm package infected 140+ projects with a hidden payload. This report highlights how to detect, hunt, and defend ...
Mastra AI’s 144 JavaScript packages was executed in just 88 minutes by North Korea’s Sapphire Sleet hacking group, which ...
CVE-2026-48907 in the Joomla JCE plugin lets unauthenticated attackers drop PHP web shells with a single crafted request.
Once a signal of exploitation risk, Willison’s ‘lethal trifecta’ describes the baseline operations of every AI agent today.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results