Hook-level agent security wins: Microsoft, Anthropic and OpenAI all shifted from gateways to runtime hooks
jacob_posel · x · 2026-10-28
jacobposel quotes @berman66's observation that agent security is shifting from gateway-level to hook-level enforcement.
The approach: run an ML model in real time on each tool call, input, or bash command, enforcing policy at runtime. Enterprises clearly want this level of control—Microsoft, Anthropic, and OpenAI have all moved to hooks. One caveat: careless deployment could generate petabytes of logs.
More from coding & agent
- Agents hate latency: Claude Opus drops APIs past 7.2s, and 'agent marketing' is born — danshipper · 2026-10-28
- LaunchMotion skills let Claude Code render 4K product launch videos in 5 minutes — yihui_indie · 2026-10-28
- Freelancer lands a Xiaohongshu gig in 5 minutes using Skillry's Motion skill — yihui_indie · 2026-10-28
- Dev rebuilds app with Rork and checks its iPhone Duo listing at Apple's SoHo store — rudrank · 2026-10-28
- Frameworks should be built for AI agents, not humans: the case for rigor over taste — samgoodwin89 · 2026-10-28
- Nous Research ships ElevenLabs SFX plugin for Hermes Agent with looping and variation tools — NousResearch · 2026-10-28