Topic
LLM
- A08 Agent Skills and MCP Security: A Survey of Scanning and Defenses A field survey of how agent skills and the Model Context Protocol went from experimental add-ons to a critical attack surface — and how scanning, red-teaming, and runtime gateways are being rebuilt to contain it.
- E09 Harness Engineering: Shipping a Self-Validating Research Pipeline With Coding Agents What it takes to make a coding agent reliably produce structured, evidence-backed research at scale — without a human babysitter and without the website ever calling an LLM.