January 20, 2026
The Coalition for Secure AI (CoSAI) has released a comprehensive whitepaper addressing Model Context Protocol (MCP)—the emerging standard that's rapidly becoming the backbone of AI agent infrastructure.
December 23, 2025
CoSAI Project Governing Board (PGB) co-chair Omar Santos explains how to operationalize the CoSAI Risk Map (CoSAI-RM) through a structured, persona-based approach that moves beyond ad-hoc security measures. Santos shares a practical, four-phase approach for turning CoSAI-RM from a conceptual model into an actionable risk management strategy, from persona-based risk […]
October 30, 2025
The Coalition for Secure AI (CoSAI) has released the AI Incident Response Framework, Version 1.0, which provides security teams with the tools, knowledge, and structured approaches they need to protect AI systems from emerging threats.
September 29, 2025
A new collaborative paper from the Coalition for Secure AI (CoSAI) introduces model signing as a foundational solution to secure the AI supply chain.
September 18, 2025
This strategic update was written by a group of CoSAI Project Governing Board members with input from the CoSAI Technical Steering Committee and workstreams. It previews upcoming papers. This update does not represent the views of all members of the CoSAI project.
July 16, 2025
Blog Post: CoSAI Principles for Secure-by-Design Agentic Systems - practical implementation strategies aimed at agent developers, adopters, and security engineers.
July 15, 2025
Blog Post: Leaders in CoSAI took a deeper look at security risk governance and how the environment is changing when it comes to AI.
June 25, 2025
The AI Supply Chain Security Imperative: 6 Critical Controls Every Executive Must Implement Now
April 28, 2025
Researchers at HiddenLayer, a CoSAI sponsor, have developed the first universal and transferable prompt injection technique that bypasses instruction guardrails across major AI models.