security

1. Jun 22, 2026 · LLM Workbench

   Securing agents at scale: what Daybreak, Codex, and AI Control mean for your run bundles

   This week's agent-security news—OpenAI's Daybreak, Samsung's Codex rollout, and DeepMind's AI Control Roadmap—reframes why audit-ready run bundles and human-in-the-loop gates matter.

   • ai-governance
   • agent-observability
   • run-bundles
   • human-in-the-loop

2. Jun 13, 2026 · LLM Workbench

   Shipping log: a stricter CSP, a calmer landing, and a demo with a sense of humor

   A few weeks of work, recapped—removing the last unsafe-eval from production, a fail-closed audit gate, and a landing page that finally feels like the product.

   • changelog
   • security
   • product

3. Jun 2, 2026 · LLM Workbench

   Hunting unsafe-eval: removing the last eval from a strict CSP

   Ajv compiled JSON-Schema validators in the browser with new Function, which forced 'unsafe-eval' into our production policy. Here's how we precompiled it away—and pinned it shut.

   • security
   • csp
   • ajv

Browse the full blog or subscribe to /feed.xml.