Signal
45 articles covering "AI coding agents"
GitHub's October 26 changelog says assisted permissions, which use a language model to judge permission requests, are generally available; its docs say the feature is not a substitute for sandboxing.
Visual Studio Code 1.143 makes the Copilot harness the default for new sessions, adds a preview of side-by-side model comparison and an experimental cleanup for inactive agent worktrees.
Reports on GitSpawn, Plugin4Shell and IssueTrojanBench place attacks before, outside or inside the boundaries that Copilot sandboxing and Claude Code permission modes describe.
OpenCode told 1.4% of Console users to revoke OpenAI, Anthropic and Google keys saved there; the company has not said how the attack worked.
Open-source projects have adopted opposing rules for AI-generated contributions, from outright bans to disclosure-optional acceptance, while a Linux Foundation survey puts incoming low-quality AI pull requests at about 25%.
Anthropic's 2.1.299 release notes for Claude Code add idle compaction for long idle terminal sessions and list fixes to sandbox symlink, glob and plugin-directory handling.
Cline's CLI v3.0.71 release notes say plugins now load inside the hub, so no JavaScript runtime is needed on PATH, and describe a new cline hub plugins status command.
GitHub's Copilot CLI changelog lists permissions.limitTo in 1.0.93 and a managed-policy option to disable Assisted Permissions in 1.0.94; GitHub's docs page does not describe either.
Claude Code 2.1.295 adds an opt-in setting that blocks an action when a command or HTTP hook fails; 2.1.294 and 2.1.296 fix hook-enforcement bugs, per release notes.
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.
GitHub put computer use into public preview in Copilot CLI and the Copilot app on macOS and Windows; it is off by default and asks approval before controlling an app.
Claude Code mods, announced October 1, are plugin-delivered TypeScript functions that can rewrite prompts and block tool calls, and Anthropic says they are not sandboxed.