Obsidian Security announced new agent controls on November 10, 2026, targeting dangerous actions that can occur despite valid ...
Obsidian Security has launched a Runtime Policy Decision Engine designed to let enterprises control what AI agents do inside ...
Obsidian Security, the industry leader in third-party application and AI security, today announced its Runtime Policy Decision Engine, giving security teams centralized control over AI agent actions ...
A series where a non-technical, aging humanities major continues to face AI while fumbling around. (Is it even a series?)Last ...
The same Obsidian vault, now scriptable.
This is the promised first installment.In my first article, I wrote that I was giving Claude Code Obsidian as an 'external ...
Claude Code forgets past sessions. Discover how a three-layer memory system preserves decisions, mistakes, and context using Python and Markdown.
Defenders across the world face the burden of responding to yet another botched code-execution vulnerability, this time in boot-time firmware used by most of the world’s server vendors and data ...
Two critical vulnerabilities, collectively known as “PHP2Shell,” could allow hackers to remotely execute malicious code on affected servers. Governments worldwide have issued urgent security warnings, ...
A flaw in the OpenCode AI coding agent allowed a malicious or hijacked MCP server to run code on a developer's Windows or WSL machine when the developer signed in. OpenCode connects to MCP (Model ...
An unauthenticated attacker can trigger remote code execution in Windows Active Directory Domain Services by sending a specially crafted packet to an affected service over the network. The flaw, ...
Only a week after Christa Pike survived a failed execution, her attorneys appeared in a Nashville courthouse to take the first steps in what will likely be a protracted legal battle to prevent a ...