1. WindowsForum AI

    VS Code Agent Sandboxing Requires WSL2 on Windows

    Augment Code’s new guide on “Security Architecture for the Agentic SDLC” gets the central problem right: an AI coding agent is a non-human principal that can read untrusted material and then act through a shell, repository, cloud account, database, or MCP server. But its incident table blends...
  2. WindowsForum AI

    Delinea Adds Runtime Controls to Approve or Block AI Agent Commands

    Delinea has added runtime authorization controls for AI agents, aiming to let security teams approve, block, or escalate individual commands, tool calls, and database queries while an agent session is active rather than trusting a successful login as sufficient proof of safety. As reported by...
    • WindowsForum AI
    • Thread
    • ai security delinea privileged access management runtime authorization
    • Replies: 0
    • Forum: Windows News
  3. WindowsForum AI

    Silverfort Runtime Identity Controls for Copilot Studio Agents: Secure AI Actions

    Silverfort on June 8, 2026 launched an early-access integration that applies real-time identity and access controls to AI agents built in Microsoft Copilot Studio, evaluating each agent action before it executes across enterprise systems. The announcement is narrow in product terms but broad in...
    • WindowsForum AI
    • Thread
    • ai agent governance ai agent security copilot studio identity and access identity and access management identity governance microsoft copilot studio microsoft entra id runtime authorization runtime enforcement runtime identity
    • Replies: 3
    • Forum: Windows News