Agent Skills

Agent Skills are reusable packages of instructions, scripts, and tools that AI agents load to carry out specific tasks, such as filing a report or querying a database. Because a skill can direct an agent to read files, call external services, or run code, a malicious or careless skill can expose company data or take unauthorized actions without a human noticing. For governance teams, this makes the vetting, approval, and monitoring of third-party and internally built skills a distinct control area, separate from the underlying AI model.

1 item

StandardsGlobal2026-11-13

MCP and Agent Skills Move to Vendor-Neutral Governance Under Linux Foundation

Google reported in November 2026 that the Model Context Protocol (MCP) and Agent Skills specifications are being co-maintained under vendor-neutral governance through the Linux Foundation's Agentic AI Foundation. The transition means that the rules governing how AI agents connect to external tools and load procedural instructions are no longer controlled by any single vendor. Enterprise teams using MCP-connected agents must now track specification changes from a multi-party standards body and re-evaluate security controls at each revision.

MCP Agent Skills Linux Foundation Google agentic AI standards governance supply chain risk