Week of Oct 20–26, 2025

Brave reports that Comet could read faint, low-contrast text embedded in images when a user asked about a screenshot, and that Fellou sent visited page text to its model on simple navigation, letting on-page instructions override user intent. Brave argues both let untrusted content trigger actions under the user's authenticated sessions.

The UK AI Security Institute, with Redwood Research, releases ControlArena, an open-source library built on Inspect for running AI control experiments. It bundles settings from simple programming problems to infrastructure-as-code codebases, attack policies, monitors and protocols such as trusted editing and defer-to-trusted, and AISI says researchers at Anthropic, Google DeepMind and Redwood have used it.

Anthropic describes sandboxing for Claude Code that restricts file writes to permitted directories and routes network traffic through a proxy that only allows approved hosts, so a prompt-injected agent cannot modify sensitive files or exfiltrate data freely. Anthropic says internal use showed an 84% reduction in permission prompts, and it released the sandbox runtime, built on bubblewrap and macOS seatbelt, as an open-source research preview.