AI security engineering: the same failures, but new ways to attack
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
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.