SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents

Language-model agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions, database records, or other state, making a later routine-looking action harmful. Yet the visible interaction may not reveal the underlying state needed to assess that action. We...

Malicious code in irashi-sead-sswe (npm)

Source: amazon-inspector 9bddece156c7b58c635468d2afce96c1fc3cf722b59e5a74aa4f8d41c84a1061 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js, autopublish.js, autopublish2.js, autopublish3.js designed ...