AI Agent Skills

Attacking and Defending Kubernetes Clusters: A Guided Tour

Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × li…

Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defense together as a closed loop,…

Use when the user wants to adversarially stress-test a guardrail, classifier, prompt, or API they own or are authorized to test, to surface the distinct ways it fails. G…

The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendat…

Explores a broad game-design space by generating structurally varied concepts, attacking obvious failures, mutating promising mechanisms, and returning a small set of di…