Digest · 2026-08-28

Close-up of a smartphone wrapped in a chain with a padlock, symbolizing strong security.

Johann Rehberger Finds a Working Prompt Injection Bypass in Opus 5 Auto Mode

Security researcher Johann Rehberger found a working prompt injection attack against Claude Code's auto mode, which Anthropic made the default and had claimed protects users against such attacks.

Close-up of wooden Scrabble tiles spelling SECURITY, symbolizing cybersecurity and protection.

best-practice

OCaml Maintainer: Exploits Now Arrive Within 10 Minutes of a Bug Rumor

Cambridge professor and OCaml maintainer Anil Madhavapeddy reports attackers probing OCaml infrastructure for exploits within about ten minutes of a security issue being shared for discussion, before any patch or release.

Retro Apple computers with keyboards displayed in a Tokyo store window, showcasing early tech design.

tool

Qwen3.8-Flash-Next: 125B Params, Only 6B Active

Qwen3.8-Flash-Next is an open-weights multimodal mixture-of-experts model from Qwen with 125B total parameters but only 6B active, described as an early preview of the Qwen4 architecture.

Close-up of a hand holding a smartphone displaying app updates on a light background.

tool

PreModelSwitch and PostModelSwitch: Claude Code Lets You Veto a Model Change

Claude Code 2.1.251 adds PreModelSwitch and PostModelSwitch hook events to block, confirm, or annotate a model switch, plus live streaming of foreground subagent tool calls to Remote Control clients.