Security on Tokenise

GitHub's new secret-detection model catches passwords that regex can't. Check the billing before you opt in

Thu, 08 Oct 2026 13:41:00 +0000

GitHub has swapped the engine behind its AI-detected secret alerts for a purpose-built model, and it’s now using the same model for two new checks aimed at the places agent-written code tends to leak: the push, and the review. The details are in GitHub’s changelog entry for October 7 .

Copilot's local sandboxing is GA. Here's what it actually restricts

Thu, 08 Oct 2026 00:01:00 +0000

GitHub announced on October 7 that local sandboxing for Copilot is generally available, across the Copilot CLI, the Copilot app and VS Code sessions that use Agent Host. It runs on Windows, macOS and Linux, and it’s included with Copilot at no extra cost . The changelog is short on detail, so the useful part is in the docs.

Claude Code mods run inside the process with your permissions. Vet them before you install

Tue, 06 Oct 2026 16:02:00 +0000

Claude Code 2.1.287 introduced mods: plugins whose JavaScript or TypeScript functions run inside the Claude Code process. They can draw panes, rewrite tool calls and add commands. They also run with your permissions and sit outside the sandbox, which makes “read it before you install it” a real step rather than a platitude.

Codex can hand its approval prompts to a reviewer agent. Here's how to set it up

Tue, 06 Oct 2026 07:06:00 +0000

Codex can stop asking you to approve every escalated command and let a second agent decide instead. It’s called auto-review, it’s a two-line config change, and it only helps if you understand what it does and doesn’t cover.

A PreToolUse hook is the guardrail that survives bypass mode

Mon, 05 Oct 2026 22:30:00 +0000

Permission prompts are only as strong as the mode you’re running in. Switch to bypass mode, or launch with --dangerously-skip-permissions, and the prompts are gone. A PreToolUse hook is different: according to the Claude Code hooks guide , it fires before any permission-mode check, and a deny from it blocks the tool even in bypassPermissions mode.

Claude Code's auto mode catches most risky actions. Anthropic's numbers show what it misses

Sat, 03 Oct 2026 07:00:00 +0000

Anthropic published how Claude Code’s auto mode works, with measured error rates. That’s unusual for a security feature, and it makes the engineering post worth reading before you let an agent run unattended. The full write-up is on Anthropic’s engineering blog.

Cursor's Security Review bot reads your pull requests for exploitable bugs

Thu, 01 Oct 2026 12:00:00 +0000

Cursor launched a Security Review bot on September 23, alongside the Rollouts deploy monitor we covered in an earlier post . It reads pull requests and reports vulnerabilities an attacker could actually exploit. Per the Cursor changelog , it’s on Teams and Enterprise plans.