Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Five Production LLMs
The episode discusses the paper "Kill-Chain Canaries," which tracks prompt injection across four stages: EXPOSED, PERSISTED, RELAYED, and EXECUTED. The hosts conclude that prompt injection is a pipeline architecture problem requiring stage-level tracking for diagnosis. Recommendations include implementing write-node placement safety primitives and using memory provenance to build trust in multi-agent systems.