The new “agentjacking” attack takes almost no real hacking ability to pull off. It's predicated on pulling a public ...
Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...
A threat actor tracked as DriveSurge has been operating large-scale malware distribution campaigns using ClickFix and FakeUpdates techniques on compromised sites. Thousands of websites have been ...
Three popular plugins served malicious JavaScript through a compromised CDN.
Researchers have revealed what they claim to be a “new class of attack” which tricks AI coding agents into executing arbitrary code on developer machines. Tenet Security, which specializes in the ...
Google Chrome is warning developers that WebMCP tools can be used to manipulate and hijack AI agents. New guidance outlines how attackers can manipulate agents operating in a user’s browser, including ...
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 ...
Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based code analysis systems into overlooking malicious payloads. Threat actors ...
Look to these key metrics and benchmarks to evaluate the performance, capability, reliability, and safety of your AI models ...
Microsoft’s AutoJack research shows how a malicious webpage rendered by an AI browsing agent can reach local MCP services and ...
Today marks the hard deadline set by the Cybersecurity and Infrastructure Security Agency for all Federal Civilian Executive Branch agencies to have remediated two actively exploited network ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results