arXiv:2611.15170 · v1

An Experience Report on Teaching Students to Evaluate AI Agent Skills as Authorization Decisions

首次提交 2026-11-11 16:07

版本更新 2026-11-11 16:07

雷达观测 2026-11-13 11:11

摘要

Cultivating a security mindset has long been a goal of computing education, and students now need it when deciding whether to trust an AI agent skill. Skills are add-ons that can shape an agent's behavior through natural language instructions and configuration settings, not just executable code. To prepare students to evaluate skills as authorization decisions, we designed a classroom activity and taught it in a senior undergraduate and a graduate cybersecurity-focused course. Students inspected three example skills, each pairing a real workflow task with one agent-specific authority, such as acting without asking for user consent before each action. The activity guided them to make initial authorization recommendations and then use a static security scanner to test and revise their recommendations. We observed in class that students needed guidance to extend their security review from a skill's code to what they would be authorizing the agent to do through the skill. Pre/post surveys from 11 volunteer respondents in this preliminary pilot showed greater self-reported confidence in evaluating skills, and post-activity responses placed more emphasis on the authority that skills carry. We release all activity materials for reuse.

作者备注：Preprint version. To appear in SIGCSE TS 2027