2 papers
cs.HC2026
Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?
Ting Yan
AI agents are poised to become a primary interface to digital products, acting across email, files, payments, and personal data. People without professional software backgrounds ne…
cs.HC2026
When "Do Not" Is Not Deny: Security Rules in CLAUDE.md vs Built-In Controls
Ting Yan
In CLAUDE.md, "do not" is a natural-language instruction that the model interprets. Claude Code's deny is a built-in control that blocks an action before the agent can take it. Bot…