Prompt-Injection

• The Reader/Writer Split: Hardening AI Agent Pipelines Against Prompt Injection March 7, 2026

  A prompt injection attempt hit our AI blog pipeline today. We refactored every combined cron into a reader/writer split -- separating the session that touches the web from the session that takes real-world actions.

• Prompt Injection Resilience: Building Hard Guards for Agentic Systems March 7, 2026

  Agentic systems that read untrusted content -- web pages, GitHub issues, email, RSS feeds -- are exposed to prompt injection at every read boundary. This post walks through the real attack surface and the defensive patterns that actually work.