Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based ...

AI agent exploited Salesforce sites; 263 objects, 55 Apex methods exposed at one portal, leading to PII and file leaks.

Python scripts were used to test malware against endpoint detection and response agents from Sophos, CrowdStrike, and Windows ...

The Agent Governance Toolkit brings runtime policy enforcement to autonomous agents, targeting the OWASP top 10 agent risks.

With its new portable memory layer, Walrus Memory lets AI agents carry context across apps, sessions and providers—putting ...

The Essential Cloud for AI™, today announced CoreWeave Sandboxes, an execution layer that gives AI researchers and platform teams secure, isolated environments for running reinforcement learning (RL), ...

AI found 21 FFmpeg zero-days, some 20 years old; Chrome 149 patched 429 bugs, including 100+ critical/high flaws.

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to breach the servers running them and make off with sensitive data and ...

AID, launched under the Linux Foundation, lets AI agents find each other through existing DNS infrastructure using SVCB ...

GitHub Copilot multi-agent support for VS Code launched at Microsoft Build 2026 alongside Project Polaris, an in-house AI ...

And it works quite well.