The new “agentjacking” attack takes almost no real hacking ability to pull off. It's predicated on pulling a public ...
Tenet Security researchers reveal how new “agentjacking” attacks could trick coding agents into executing arbitrary code ...
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 ...
Chrome's WebMCP guidance warns that AI agents can be manipulated through the tools they are built to trust.
Three popular plugins served malicious JavaScript through a compromised CDN.
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 ...
Look to these key metrics and benchmarks to evaluate the performance, capability, reliability, and safety of your AI models ...
Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based ...
Microsoft’s AutoJack research shows how a malicious webpage rendered by an AI browsing agent can reach local MCP services and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results