A new attack technique dubbed HalluSquatting turns AI assistants’ tendency to hallucinate into a scalable infection vector.
As Google releases yet another Chrome security update, here’s what you need to know about use-after-free flaws.
The flaw, which impacted Amazon, Anthropic, Google, Cursor and others, let the agent give the human false information on ...
Researchers warn AI agents could be tricked into downloading malicious code by exploiting hallucinations that cause chatbots ...
JadePuffer could be the first reported case of a ransomware attack driven by AI from start to finish. How can businesses ...
An "agentic threat actor" successfully exploited a Langflow flaw to steal data from a production database server and encrypt ...
Security researchers say an autonomous AI agent carried out a complete ransomware attack, adapting to failures and executing ...
Lazarus Group concealed a four-module remote access toolkit inside six fake npm Rollup polyfill packages that fired at import ...
Researchers identified what they believe is the first documented case of a ransomware operation, JadePuffer, conducted ...
The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system.
CISA added a Microsoft SharePoint RCE flaw to its exploited bugs catalog after confirming active attacks on unpatched servers ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results