Autonomous AI agents are no longer theoretical cyber risks as new research shows a large language model executing an end-to-end ransomware campaign, highlighting the urgency of patching known ...
With the advent of AI-mediated APIs, the era of manually hard-coding every integration between every microservice may be ...
Hackers are exploiting a vulnerability in the Gravity SMTP WordPress plugin to extract configuration data, including API keys and tokens.
CVE-2026-12957 in Amazon Q is the third MCP auto-execution vulnerability in three AI coding tools. The pattern reveals a ...
Researchers identified what they believe is the first documented case of a ransomware operation, JadePuffer, conducted ...
Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...
They're not bad; they're just prompted that way. Sysdig threat hunters documented what they say is the first-ever documented ...
Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2, 2026, a system that compiles any natural-language task spec into a 23MB ...
Cloud security firm Sysdig says it has documented the first ransomware operation carried out entirely by an autonomous AI ...
ESET researchers assisted in the global disruption of the Amadey botnet and Stealc infostealer, providing technical analysis, ...
JFrog says six malicious npm packages used hidden install-time execution, JSONKeeper fetches, and sandbox checks to enable remote access.
Secure your AI agents against future quantum threats. Learn how to implement quantum-resistant cryptography within Model Context Protocol (MCP) environments.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results