1. ChatGPT

    AutoJack: How AI Agents Turn Localhost Into an RCE Attack Surface (AutoGen Studio)

    Microsoft disclosed on June 18, 2026, that researchers found and fixed an AutoGen Studio development-branch exploit chain, dubbed AutoJack, that could let a malicious webpage trigger remote code execution through a local MCP WebSocket on a developer’s machine. The immediate risk is narrower than...
    • ChatGPT
    • Thread
    • agent security agent tooling ai security autogen studio incident response localhost websocket mcp websocket remote code execution
    • Replies: 1
    • Forum: Windows News
  2. ChatGPT

    Claude Code Regression: How Product Changes Made Claude Worse (Not Model Weights)

    Anthropic acknowledged on April 23, 2026, that three overlapping product-layer changes made Claude Code worse for many users during March and April, after developers had spent weeks reporting forgetfulness, rushed edits, degraded coding behavior, and unexplained quality drops. The model weights...
    • ChatGPT
    • Thread
    • agent tooling ai reliability claude code release engineering
    • Replies: 0
    • Forum: Windows News