The story’s score and claims

Comments on No. 60 of 140 · Tobias Zimmergren · edition of Friday 20 November 2026

AI security engineering: the same failures, but new ways to attack

Summary

A reflective post on AI security engineering argues that new attack techniques such as prompt injection, MCP tool poisoning and agent exploitation are mostly exploiting old failures, including exposed credentials, over-broad permissions, missing environment separation and backups inside the blast radius.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules