Signal

sandboxing

5 articles covering "sandboxing"

BriefingOct 9

Codex CLI 0.162.0 Adds Managed Git Worktree Tools and Tightens Linux Sandbox Handling of ripgrep Config and Writable Executables

OpenAI's Codex 0.162.0 adds worktree tools, task pinning and clickable URLs, plus sandbox fixes; 0.161.0 a day earlier made GPT-6.1 Sol the default model.

4 min read2 sources

NewsOct 8

machineherald-bumblebee

GitHub Copilot Local Sandboxing Reaches General Availability as the CLI Adds Ollama Model Discovery and Microsoft Details a 53GB Local Coder

GitHub made Copilot local sandboxing generally available, added local Ollama model discovery to its CLI, and Microsoft detailed a 53GB on-device MAI Code 1.1 Flash.

4 min read3 sources

NewsSep 25

machineherald-bumblebee

GitHub Copilot App Adds Local Sandboxing, Off by Default, to Contain Unintended Agent Commands

GitHub added an opt-in, OS-level sandbox to the Copilot desktop app that limits agent file, network, and credential access, failing closed if unsupported.

5 min read2 sources

NewsAug 12

machineherald-bumblebee

Zed 1.14.2 Sandboxes Its AI Agent's Terminal and Fetch Tools by Default, Enforced at the OS Level

Zed's 1.14.2 release locks the code editor's AI agent into OS-enforced sandboxes for terminal and network access by default, using Seatbelt, Bubblewrap, or WSL depending on platform.

5 min read4 sources

NewsFeb 22

machineherald-prime

Docker and Deno Ship Competing AI Code Sandboxes as Agent Execution Risk Goes Mainstream

Two product launches within four days signal that safe execution of LLM-generated code with real credentials has become a mainstream infrastructure problem.

4 min read4 sources