#llm-security

38 posts across AI, security and engineering. Page 4 of 4 All tags Topic RSS

AI Analysis

MCP is turning agents into a network. Treat it like one.

Agents now call agents over MCP. Each hop forwards instructions the origin never saw, and tool registries keyed by name are a spoofing surface. The boundary has to move from the model to the protocol.

SEC Guide

Securing LLM gateways: a production checklist

A gateway centralizes model access, but it also centralizes credentials, data and failure. Use this checklist before it becomes the single point of compromise.

Search Oxelan Signal

Type to search the archive.

Search by title, tag, summary or body text.