AGENT SECURITY

A guard hook that crashes, times out or points at a missing script lets the tool call through by default in Claude Code. v2.1.295 adds onFailure: block. Here is what each coding agent does when your policy hook breaks, with real test runs.

Copilot CLI 1.0.94 finds local Ollama models from /model and ships an OS-level sandbox. Setup, the 4k context trap, and why local is not offline.

A deny rule on .env stops cat but not a Python one-liner. Here are the three layers that actually keep secrets out of a coding agent's context - file rules, environment scrubbing and credential masking - and what Claude Code, Codex, Cursor and Gemini CLI give you for each, with real test runs.

Google's new Gemini agent can spin up coworker agents with their own Workspace account, email address and audit trail. What Google announced, what it left out, and what builders should copy.

Claude Code mods are plugins whose JavaScript handlers run inside Claude Code itself. What they can do that hooks and skills cannot, a first mod you can run today, and the trust question you must settle first.

OpenAI Dots turns ChatGPT into a long-running work agent. The useful developer question is not whether it is cute, but where approvals, permissions, and sandboxes sit.

Cloudflare AI Gateway now attaches a verified user identity to every request and learns a behavioral baseline per account, flagging 2x-p95 session spikes against an org-wide p99 ceiling. Here is how the anomaly math works and why per-account baselines beat global thresholds.

Microsoft Execution Containers (MXC) give your AI agents policy-driven sandboxing across Windows, Linux, and macOS. TypeScript SDK, JSON config, multiple isolation backends. Here is how to use it.