Filings tagged: AI
Practical thinking on security, infrastructure, and AI. No thought leadership for the sake of it.
-
Prompt injection is not the new SQL injection
16 February 2026 · AI Security Commentary
Schneier and co have reframed prompt injection as 'promptware' — a full 7-stage kill chain. The uncomfortable truth: LLMs can't distinguish instructions from data. This isn't a bug you can patch.