Is Claude Code Secure? Let’s Find Out!
Vulnerable Plugin + MCP Enumeration TL&DR Claude Code didn’t invent most of the security problems discussed in this article but it will make them faster, louder and easier to repeat. As I rush to use AI myself, I realize the attack surface is widening in ways that follow classic software supply chain weaknesses: With a…
Anthropic’s Security Layers Explained: The Good, Bad & Ugly
Can you secure the Anthropic SaaS cloud platform? The answer, sorta, kinda, maybe. This article is intended for architects and managers. Low level embedded security analysis is in the works for next week in another article. Let me say ahead of time, huge shout out to Anthropic, I personally respect the company a ton and…
AI RED TEAMING – man-in-the-vector Attack & custom Tooling
Want deeper dives into AI vector embedding attack vectors? See more at Security Sandman. This article provides practical examples to assist red teams and security researches to find and exploit vulnerable AI systems using Vector Databases and even flow chaining tools. I’ve prototyped some simple tools to demonstrate the attack chain and later I’ll finish…
@secSandman 