Archive: https://archive.today/v71LL From the post: TL;DR The paper names 'self-state attacks': an agent is compromised by corruption of its own memory or config files via legitimate OS system calls. The authors map the threat as a 23-cell matrix across four axes (Target, Mechanism, Granularity, Temporal) with 43 concrete file operations. Their recommended layered defense left four attack cells 'structurally indistinguishable' at the OS level, concentrated on memory-file writes.