If you’re part of an organization that’s currently rushing into the AI fray, do you have the controls and guidance in place to handle hallucinations when they come to call? Or are you trusting that your software or model will prevent them?
The MCP standard gave rise to dreams of interconnected agents and nightmares of what those interconnected agents would do with unfettered access to APIs, data, and local systems. Aaron Parecki explains how OAuth's new Client ID Metadata Documents spec provides more security for MCPs and the reasons why the behavior and design of MCPs required a new...
Secure code should be grounded more in concepts like secure by default and secure by design than by "spot the vuln" thinking. Matias Madou shares his experience in secure coding training and the importance of teaching critical thinking. He also discusses why critical thinking is so closely related to threat modeling and how LLMs can be a tool for h...
Fast Five
Selected by the SC Media Editorial team every Tuesday.
Sign up now for the top five issues cybersecurity pros need to know this week.
