Evaluating a Layered Prompt-Injection Defence for the Model Context Protocol: A Record-Level Audit of Decision Conventions, Corpus Provenance and Reproducibility.

arXiv:2604.17125v3 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) extends the prompt-injection attack surface of large language model applications to tool descriptions, parameter schemas and tool outputs. Defences for it report detecti