Skip to content
RETRIDGE
← RAG Engineering Notes
AI Security Draft · 11 min read

Prompt injection: the security hole most AI teams ship with

Retridge Engineering
RAG & evaluation practice
Draft · not yet published

This note is on the editorial calendar. The outline below shows the intended structure; the article layout, code styling, and diagram treatment are the same as published notes.

Planned outline
Direct vs indirect injection, and why indirect is the real risk
Injection through retrieved documents and connected tools
Why input filtering is mitigation, not a control
Access boundaries: retrieval scope as a security perimeter
A minimal red-team suite for enterprise RAG
What to log so you can tell an attack from a bug

In the meantime, the published note on retrieval-versus-correctness covers the measurement approach these all build on.

RAG Engineering Notes

One note a month on retrieval quality, evaluation, and AI security. No marketing.