Most engineering teams use GitHub more like a file cabinet, with well-organized contents, instantiating code, setting up a pipeline, and leaving the settings page mostly untouched. This approach made sense when GitHub was only version control. Now, GitHub is in…
Have you forgotten how you can ship code without documenting all the components within it? Those days are gone. I began to take an interest in Software Bill of Materials (SBOM) after completing a project that was flagged as using…
In December 2020, during the SolarWinds breach, I remember thinking it was another advanced hack. However, after reviewing the technical report and observing the way offenders changed the playbook in the following five years, it became obvious: SolarWinds was not…
I understand, of course, that when you hear the term software supply chain security, you think it is another buzzword from salespeople. However, since SolarWinds made it apparent that a single breach of a build system can cost corporations and…
AI agents no longer answer questions; instead, they book meetings, update databases, and transfer money. That shift from helper to independent worker changes everything about aspects of security. The challenge? Most security structures were designed for traditional applications, not for…
Ey, independent AI agents are no longer fancy chatbots. They make decisions, build APIs, and coordinate workflows without constant human oversight. That said, they also require stringent governance systems in place before the situation runs amok. I have been experimenting…
Well, I have spent a fair amount of time as an agent system hacker, and I can tell they are not as impregnable as the hype makes them seem. Once you put two or more AI agents in the room,…
And today AI agents are ubiquitous. They respond to customer support tickets, write code, maintain workflows, and make decisions that a human would otherwise have to make. But no one talks much about what happens when these agents go rogue,…
By the way, I spent the last few months testing various sLLM-based tools, and something kept bothering me. Why then did some of the AI agents abruptly begin to act strange after some sessions? It turns out that I was…
Feel free to believe me: the first thing that crossed my mind when I was told about the concept of memory poisoning in AI systems was a matter of science fiction. After that, I began researching the specifics of how…
Autonomous agents are not text-generating chatbots. They are powerful AI systems that can email messages, query databases, read the Internet, and make decisions using more across multiple steps- the very thing that endangers them insofar as a person learns to…
Look, chatbots are one thing. You ask a question, you get an answer; it may be bad, it may be useful, but it stays on its path. Agentic AI? That is another thing altogether. These systems do not simply respond.…